KR102594697B1 - Method and apparatus for rebalancing a portfolio for virtual assets according to a state of the virtual asset market using a neural network - Google Patents

Abstract

Embodiments present a method and device for performing rebalancing on a portfolio for virtual assets by a portfolio management server using a neural network. According to one embodiment, the method comprises: a step of receiving a first message; a step of obtaining transaction information by exchange; a step of extracting data on a plurality of variables; a step of determining a plurality of evaluation scores through an evaluation model; a step of determining rebalancing information; a step of transmitting a second message; and a step of performing rebalancing.

Description

Method and apparatus for performing rebalancing on a portfolio for virtual assets according to the state of the virtual asset market using a neural network {METHOD AND APPARATUS FOR REBALANCING A PORTFOLIO FOR VIRTUAL ASSETS ACCORDING TO A STATE OF THE VIRTUAL ASSET MARKET USING A NEURAL NETWORK}

Embodiments of the present disclosure relate to technology for performing rebalancing on a portfolio of virtual assets, and technology for performing rebalancing on a portfolio of virtual assets according to the state of the virtual asset market using a neural network. will be.

Meanwhile, although the virtual asset market such as cryptocurrency has grown rapidly, there is a lack of asset management methods that take into account the characteristics of virtual assets, only using asset management methods in the existing stock market for the rapidly growing virtual asset market.

In particular, because the cryptocurrency market lacks a suitable sample that can be used as a benchmark and the rate of return is highly variable compared to the existing stock market, it can be difficult to manage a cryptocurrency portfolio using techniques used in the stock market. there is.

Additionally, because the stability of the cryptocurrency market is not managed nationally, it is necessary to evaluate the stability of the cryptocurrency market through stability indicators that take into account the characteristics of cryptocurrency.

Accordingly, the soundness of the cryptocurrency market is evaluated based on transaction data using indices suitable for the cryptocurrency market, and the existing cryptocurrency portfolio is created through an evaluation model using a neural network according to the soundness of the cryptocurrency market. A method of rebalancing the portfolio to one with the lowest risk relative to profitability is needed.

Embodiments of the present disclosure may provide a method and apparatus for rebalancing a portfolio of virtual assets according to the state of the virtual asset market using a neural network.

The technical challenges to be achieved in the embodiments are not limited to the matters mentioned above, and other technical challenges not mentioned may be considered by those skilled in the art from the various embodiments described below. You can.

A method in which a portfolio management server performs rebalancing on a portfolio of virtual assets using a neural network according to an embodiment includes receiving portfolio information about the virtual asset from a user terminal, Transaction information on the trading items included in the portfolio information is acquired for each exchange at each cycle set in the portfolio management server, and data on a plurality of first variables is extracted based on the transaction information on the trading items obtained at each cycle. And, the plurality of first variables include market capitalization, transaction execution price, sell price, bid price, section of ask price, section of bid price, transaction volume for each section, order volume for each section, and cancellation transaction volume for each section, and the plurality of first variables include The market health is determined for each cycle based on data on the first variable, and based on the market health being below a preset threshold, the market health is determined from the time the user holds the virtual asset. Data on a plurality of second variables are extracted from transaction information on the trading item for the trading period up to the point when the trading period decreases below the threshold, and the plurality of second variables are total return, profit, etc. for the trading period. The average return per trade for trades that incurred losses, the average return per trade for trades that incurred losses, the standard deviation of returns for trades that resulted in profits, the standard deviation of the drawdown rate for trades that incurred losses, the total number of trades and the win percentage. Comprising: determining a plurality of evaluation scores through an evaluation model using a neural network based on data on the plurality of second variables, and performing rebalancing on the portfolio based on the plurality of evaluation scores. may include.

For example, the evaluation score is a first value applied with a first weight to the standard deviation of the rate of return for profitable transactions within the trading period and a first weight applied to the standard deviation of the loss rate for transactions with a loss within the trading period. It may be the sum of the second value applied with the second weight having a smaller value divided by the average annual rate of return for the trading period.

For example, the market health refers to the price change value including the trading volume canceled after a transaction was ordered on the exchange within the cycle, the first change value determined based on the actual price change value within the cycle, and the valid quote price within the cycle. It may be determined according to the second change value determined based on the value minus the price within the cycle.

For example, rebalancing of the portfolio may be performed according to the proportion of virtual assets. The proportion of the virtual asset may be determined based on the number of transactions per day, the expected profit/loss ratio per transaction, and the plurality of evaluation scores. The number of transactions per day may be the total number of transactions divided by the transaction period. The expected profit/loss ratio per transaction can be determined based on the win rate within the transaction period, the average return per transaction for profitable transactions within the transaction period, and the average loss rate per transaction for transactions with losses within the transaction period. there is.

According to one embodiment, the market health may be determined by the following equation.

In the above equation, s is the market health, N is the trading volume that occurred during the period, c is a weight according to the market capitalization of the trading item, and M _ai is the exchange rate for each of the N transactions. is the sum of the price changes including the transaction volume canceled after the transaction was ordered, M _bi is the sum of the actual price changes for each of the N transactions, and P _vi is the N transactions. It is a value obtained by adding up the effective quotation prices for each, where P _ri is a value summing up the execution price for each of the N transactions, and P _d may be a default value for each of the N transactions.

Additionally, according to one embodiment, the evaluation score may be determined by the following equation.

In the above equation, the StrategyValueScore is the evaluation score, the Total Profit is the total return, the TradingDay is the trading period, and the Profit sd(+) is the standard deviation of returns for transactions that generated profits within the trading period. , the Profit sd(-) may be the standard deviation of the loss rate for transactions in which losses occurred within the trading period.

According to one embodiment, the neural network may include an input layer, one or more hidden layers, and an output layer. Each learning data consisting of data for a plurality of variables and a plurality of evaluation scores of the correct answer is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector, and the output vector is It is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each training data, and the parameters of the neural network are It can be learned in a way that the loss value becomes smaller.

For example, the plurality of evaluation scores may be determined for each transaction time interval for a plurality of trading algorithms. The plurality of transaction algorithms can be set for each virtual asset. Each of the above virtual assets can be set for each exchange. The plurality of trading algorithms include a first algorithm in which transactions are concluded based on the standard deviation of the price fluctuation section determined based on the Blink reflection indicator, a second algorithm in which transactions are concluded based on a preset moving average, and a current algorithm. It may include a third algorithm in which transactions are concluded according to the average value of the change range of candles for the previous positive and negative candles. The blink reflection indicator may be an indicator that calculates the deviation by adding the price change when a transaction occurs and the price change that may occur, including the quantity canceled after the quote is submitted within the price change range.

Additionally, for example, the proportion of the household assets may be determined by the following equation.

In the above equation, the Cap is the proportion of the virtual asset, the Trade per Day is the number of times the virtual asset is traded per day, the Expect P&L is the expected profit/loss ratio per transaction for the virtual asset, and the TSVS is a comprehensive evaluation score for the virtual asset, n is the number of transaction items, and TSVS _i may be a comprehensive evaluation score for the ith transaction item.

Here, the Trade per Day may be the total number of transactions divided by the trading period. Here, the Expect P&L may be determined based on the win rate within the trading period, the average return per transaction for profitable transactions within the trading period, and the average return per transaction for transactions with loss within the trading period. Here, the comprehensive evaluation score may be a score determined based on a plurality of evaluation scores determined for the virtual asset. For example, the comprehensive evaluation score may be a weighted average value that reflects the weight of the rebalancing criteria in a plurality of evaluation scores.

For example, the frequency of preset words may be determined based on text data collected through web crawling performed by the portfolio management server. The period can be adjusted according to the frequency of the preset words. The preset threshold may be adjusted according to the frequency of the preset word.

Additionally, for example, the portfolio management server exchanges transaction information on trading items included in the portfolio information according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling. You can change the acquisition cycle from the server. For example, the portfolio management server may change the preset threshold value according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling.

According to embodiments, the portfolio management server determines the market health based on various transaction data extracted from transaction information on transaction items related to virtual assets, thereby reflecting the amount of impact in the cryptocurrency market with respect to the range of price fluctuations. The health of the market can be effectively judged.

According to embodiments, the portfolio management server can continuously monitor market health by determining market health according to a set cycle, and adaptively manage the portfolio by changing the cycle value according to market conditions. You can.

According to embodiments, the portfolio management server determines a plurality of evaluation scores through an evaluation model using a neural network based on various factors, and rebalances the portfolio based on the plurality of evaluation scores to maximize risk compared to profitability. You can rebalance to a lower portfolio.

According to embodiments, when determining an evaluation score, the portfolio management server may determine an evaluation score that reflects the characteristics of the virtual asset by using an indicator changed into a suitable form to evaluate the algorithm for the virtual asset.

The effects that can be obtained from the examples are not limited to the effects mentioned above, and other effects not mentioned can be clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and together with the detailed description describe technical features of the various embodiments.
1 is a diagram showing the configuration of an electronic device according to an embodiment.
Figure 2 is a diagram showing the configuration of a program according to one embodiment.
Figure 3 shows a system that performs rebalancing on a portfolio of virtual assets using a neural network according to an embodiment.
Figure 4 shows a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment.
Figure 5 is a flowchart of a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment.
Figure 6 is an example of an evaluation model according to one embodiment.
Figure 7 is a block diagram showing the configuration of a portfolio management server according to an embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. Additionally, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may change. Some features or features of one embodiment may be included in other embodiments or may be replaced with corresponding features or features of other embodiments.

In the description of the drawings, procedures or steps that may obscure the gist of the various embodiments are not described, and procedures or steps that can be understood at the level of a person with ordinary knowledge in the relevant technical field are not described. did.

Throughout the specification, when a part is said to “comprise or include” a certain element, this means that it does not exclude other elements but may further include other elements, unless specifically stated to the contrary. do. In addition, terms such as "... unit", "... unit", and "module" used in the specification refer to a unit that processes at least one function or operation, which refers to hardware, software, or a combination of hardware and software. It can be implemented as: Additionally, the terms “a or an,” “one,” “the,” and similar related terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, it may be used in both singular and plural terms.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the attached drawings. The detailed description set forth below in conjunction with the accompanying drawings is intended to illustrate exemplary embodiments of various embodiments and is not intended to represent the only embodiment.

In addition, specific terms used in various embodiments are provided to aid understanding of the various embodiments, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the various embodiments. .

1 is a diagram showing the configuration of an electronic device according to an embodiment.

1 is a block diagram of an electronic device 101 in a network environment 100, according to various embodiments. Referring to FIG. 1, in the network environment 100, the electronic device 101 communicates with the electronic device 102 through a first network 198 (e.g., a short-range wireless communication network) or a second network 199. It is possible to communicate with at least one of the electronic device 104 or the server 108 through (e.g., a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108. According to one embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, and a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or may include an antenna module 197. In some embodiments, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added to the electronic device 101. In some embodiments, some of these components (e.g., sensor module 176, camera module 180, or antenna module 197) are integrated into one component (e.g., display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (e.g., program 140) to operate at least one other component (e.g., hardware or software component) of the electronic device 101 connected to the processor 120. It can be controlled and various data processing or calculations can be performed. According to one embodiment, as at least part of data processing or computation, the processor 120 stores commands or data received from another component (e.g., sensor module 176 or communication module 190) in volatile memory 132. The commands or data stored in the volatile memory 132 can be processed, and the resulting data can be stored in the non-volatile memory 134. According to one embodiment, the processor 120 includes a main processor 121 (e.g., a central processing unit or an application processor) or an auxiliary processor 123 that can operate independently or together (e.g., a graphics processing unit, a neural network processing unit ( It may include a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device 101 includes a main processor 121 and a secondary processor 123, the secondary processor 123 may be set to use lower power than the main processor 121 or be specialized for a designated function. You can. The auxiliary processor 123 may be implemented separately from the main processor 121 or as part of it.

The auxiliary processor 123 may, for example, act on behalf of the main processor 121 while the main processor 121 is in an inactive (e.g., sleep) state, or while the main processor 121 is in an active (e.g., application execution) state. ), together with the main processor 121, at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190) At least some of the functions or states related to can be controlled. According to one embodiment, co-processor 123 (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module 180 or communication module 190). there is. According to one embodiment, the auxiliary processor 123 (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models.

Artificial intelligence models can be created through machine learning. For example, such learning may be performed in the electronic device 101 itself on which the artificial intelligence model is performed, or may be performed through a separate server (e.g., server 108). Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101. Data may include, for example, input data or output data for software (e.g., program 140) and instructions related thereto. Memory 130 may include volatile memory 132 or non-volatile memory 134.

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142, middleware 144, or application 146.

The input module 150 may receive commands or data to be used in a component of the electronic device 101 (e.g., the processor 120) from outside the electronic device 101 (e.g., a user). The input module 150 may include, for example, a microphone, mouse, keyboard, keys (eg, buttons), or digital pen (eg, stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101. The sound output module 155 may include, for example, a speaker or a receiver. Speakers can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 can visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector, and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of force generated by the touch.

The audio module 170 can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device (e.g., directly or wirelessly connected to the electronic device 101). Sound may be output through the electronic device 102 (e.g., speaker or headphone).

The sensor module 176 detects the operating state (e.g., power or temperature) of the electronic device 101 or the external environmental state (e.g., user state) and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 includes, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that can be used to connect the electronic device 101 directly or wirelessly with an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 can convert electrical signals into mechanical stimulation (e.g., vibration or movement) or electrical stimulation that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 can capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 can manage power supplied to the electronic device 101. According to one embodiment, the power management module 188 may be implemented as at least a part of, for example, a power management integrated circuit (PMIC).

The battery 189 may supply power to at least one component of the electronic device 101. According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

Communication module 190 is configured to provide a direct (e.g., wired) communication channel or wireless communication channel between electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108). It can support establishment and communication through established communication channels. Communication module 190 operates independently of processor 120 (e.g., an application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (e.g., : LAN (local area network) communication module, or power line communication module) may be included. Among these communication modules, the corresponding communication module is a first network 198 (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (e.g., legacy It may communicate with an external electronic device 104 through a telecommunication network such as a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into one component (e.g., a single chip) or may be implemented as a plurality of separate components (e.g., multiple chips). The wireless communication module 192 uses subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 can be confirmed or authenticated.

The wireless communication module 192 may support 5G networks after 4G networks and next-generation communication technologies, for example, NR access technology (new radio access technology). NR access technology provides high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low latency). -latency communications)) can be supported. The wireless communication module 192 may support high frequency bands (eg, mmWave bands), for example, to achieve high data rates. The wireless communication module 192 uses various technologies to secure performance in high frequency bands, for example, beamforming, massive array multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. It can support technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module 192 may support various requirements specified in the electronic device 101, an external electronic device (e.g., electronic device 104), or a network system (e.g., second network 199). According to one embodiment, the wireless communication module 192 supports Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mmTC, or U-plane latency (e.g., 164 dB or less) for realizing URLLC. Example: Downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) can be supported.

The antenna module 197 may transmit or receive signals or power to or from the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator made of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is connected to the plurality of antennas by, for example, the communication module 190. can be selected Signals or power may be transmitted or received between the communication module 190 and an external electronic device through the at least one selected antenna. According to some embodiments, in addition to the radiator, other components (eg, radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module 197.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, a mmWave antenna module includes: a printed circuit board, an RFIC disposed on or adjacent to a first side (e.g., bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., mmWave band); And a plurality of antennas (e.g., array antennas) disposed on or adjacent to the second side (e.g., top or side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (e.g., bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( (e.g. commands or data) can be exchanged with each other.

According to one embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199. Each of the external electronic devices 102 or 104 may be of the same or different type as the electronic device 101. According to one embodiment, all or part of the operations performed in the electronic device 101 may be executed in one or more of the external electronic devices 102, 104, or 108. For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 may perform the function or service instead of executing the function or service on its own. Alternatively, or additionally, one or more external electronic devices may be requested to perform at least part of the function or service. One or more external electronic devices that have received the request may execute at least part of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device 101. The electronic device 101 may process the result as is or additionally and provide it as at least part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology can be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide services to the connected electronic device 101. In addition, the server 108 may perform a membership registration process, store and manage various information of users who have registered as members, and provide various purchase and payment functions related to the service. Additionally, the server 108 may share execution data of service applications running on each of the plurality of electronic devices 101 in real time so that services can be shared between users. This server 108 may have the same hardware configuration as a typical web server or service server. However, in terms of software, it may be implemented through any language such as C, C++, Java, Python, Golang, and Kotlin and may include program modules that perform various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives work performance requests from clients or other servers and derives and provides work results in response. It refers to a computer system and the computer software (server program) installed for it. In addition, in addition to the server program described above, the server 108 includes a series of application programs running on the server 108 and, in some cases, various databases (DBs) built internally or externally, hereinafter " It should be understood as a broad concept including “DB”). Accordingly, the server 108 classifies membership registration information and various information and data about games, stores them in a DB, and manages this DB, which may be implemented inside or outside the server 108. In addition, the server 108 can be implemented using a variety of server programs provided on general server hardware and operating systems such as Windows, Linux, UNIX, and Macintosh. , Representative examples include IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, and TOMCAT used in a Unix environment, etc., to implement web services. Additionally, the server 108 may be linked with an authentication system and payment system for user authentication of the service or payment for purchases related to the service.

The first network 198 and the second network 199 are a connection structure that allows information exchange between each node, such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. It means (Network). The first network 198 and the second network 199 are the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), and 3G. , 4G, LTE, 5G, Wi-Fi, etc., but are not limited to these. The first network 198 and the second network 199 may be closed, such as a LAN or WAN, but are preferably open, such as the Internet. The Internet includes protocols such as TCP/IP protocol, TCP, and UDP (user datagram protocol), as well as various services that exist at the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), a worldwide open computer primary network (198) and secondary network (199) that provides Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) refers to the structure.

A database can have a general data structure implemented in the storage space (hard disk or memory) of a computer system using a database management program (DBMS). A database may have a data storage format that allows for free search (extraction), deletion, editing, addition, etc. of data. Databases are relational database management systems (RDBMS) such as Oracle, Infomix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and an XML native database such as Excelon, Tamino, and Sekaiju, and has its own functions. To achieve this, you can have appropriate fields or elements.

Figure 2 is a diagram showing the configuration of a program according to one embodiment.

Figure 2 is a block diagram 200 illustrating program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable on the operating system 142 for controlling one or more resources of the electronic device 101. It can be included. Operating system 142 may include, for example, AndroidTM, iOSTM, WindowsTM, SymbianTM, TizenTM, or BadaTM. At least some of the programs 140 are preloaded into the electronic device 101, for example, at the time of manufacture, or are stored in an external electronic device (e.g., the electronic device 102 or 104, or a server) when used by a user. It can be downloaded or updated from 108)). All or part of the program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or retrieval) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively operate on other hardware devices of electronic device 101, such as input module 150, audio output module 155, display module 160, and audio module 170. , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that functions or information provided from one or more resources of the electronic device 101 can be used by the application 146. The middleware 144 includes, for example, an application manager 201, a window manager 203, a multimedia manager 205, a resource manager 207, a power manager 209, a database manager 211, and a package manager 213. ), connectivity manager (215), notification manager (217), location manager (219), graphics manager (221), security manager (223), call manager (225), or voice recognition manager (227). You can.

The application manager 201 may, for example, manage the life cycle of the application 146. The window manager 203 may, for example, manage one or more GUI resources used on the screen. For example, the multimedia manager 205 identifies one or more formats required for playing media files, and encodes or decodes the corresponding media file using a codec suitable for the selected format. It can be done. The resource manager 207 may, for example, manage the source code of the application 146 or the memory space of the memory 130. The power manager 209 manages, for example, the capacity, temperature, or power of the battery 189, and may use this information to determine or provide related information necessary for the operation of the electronic device 101. . According to one embodiment, the power manager 209 may interface with a basic input/output system (BIOS) (not shown) of the electronic device 101.

Database manager 211 may create, search, or change a database to be used by application 146, for example. The package manager 213 may, for example, manage the installation or update of applications distributed in the form of package files. The connectivity manager 215 may manage, for example, a wireless connection or direct connection between the electronic device 101 and an external electronic device. For example, the notification manager 217 may provide a function for notifying the user of the occurrence of a designated event (eg, an incoming call, message, or alarm). The location manager 219 may, for example, manage location information of the electronic device 101. The graphics manager 221 may, for example, manage one or more graphic effects to be provided to the user or a user interface related thereto.

Security manager 223 may provide, for example, system security or user authentication. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101. For example, the voice recognition manager 227 transmits the user's voice data to the server 108 and provides a command corresponding to a function to be performed in the electronic device 101 based at least in part on the voice data, Alternatively, text data converted based at least in part on the voice data may be received from the server 108. According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least a portion of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142.

The application 146 includes, for example, home 251, dialer 253, SMS/MMS (255), instant message (IM) 257, browser 259, camera 261, and alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Album (275), Watch (277), Health (279) (such as exercise amount or blood sugar) It may include applications that measure biometric information) or environmental information 281 (e.g., measure atmospheric pressure, humidity, or temperature information). According to one embodiment, the application 146 may further include an information exchange application (not shown) that can support information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to deliver designated information (e.g., calls, messages, or alarms) to an external electronic device, or a device management application configured to manage the external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a specified event (e.g., mail reception) generated in another application (e.g., email application 269) of the electronic device 101 to an external electronic device. You can. Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide it to the user of the electronic device 101.

The device management application, for example, controls the power (e.g., turn-on or turn-off) of an external electronic device or some component thereof (e.g., a display module or camera module of the external electronic device) that communicates with the electronic device 101. ) or functions (such as brightness, resolution, or focus). A device management application may additionally or alternatively support installation, deletion, or update of applications running on external electronic devices.

Throughout this specification, neural network, neural network, and network function may be used with the same meaning. A neural network may consist of a set of interconnected computational units, which may generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two or more nodes. Nodes (or neurons) that make up neural networks may be interconnected by one or more “links.”

Within a neural network, two or more nodes connected through a link can relatively form a relationship as an input node and an output node. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, nodes connecting the input node and the output node may have weights. Weights may be variable and may be varied by a user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if there are two neural networks with the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

Meanwhile, in various embodiments of the present disclosure, the virtual asset may be cryptocurrency. Cryptocurrency is a compound word of 'crypto-', meaning 'encryption', and 'currency', meaning 'currency'. It is safely transmitted through public key encryption in a distributed ledger and can be easily owned using a hash function. It is a digital asset that can prove. In general, cryptocurrency can operate on a distributed ledger based on blockchain or DAG (directed acyclic graph).

Figure 3 shows a system that performs rebalancing on a portfolio of virtual assets using a neural network according to an embodiment. One embodiment of FIG. 3 may be combined with various embodiments of the present disclosure.

Referring to FIG. 3, the system 30 for rebalancing a portfolio for virtual assets includes a portfolio management server 310, a user terminal 320, an exchange server 330, a network 340, and a database ( 350).

The portfolio management server 310 may receive portfolio information about virtual assets from the user terminal 320 through the network 340. The portfolio management server 310 receives a message requesting rebalancing of the portfolio for virtual assets from the user terminal 320 through the network 340, and rebalances the portfolio related to the user terminal 320 (information ( Hereinafter, rebalancing information) may be transmitted to the user terminal 320. For example, portfolio management server 310 may include server 108 of FIG. 1 .

For example, the portfolio management server 310 may provide the user terminal 320 with a user interface for rebalancing virtual assets and transmit rebalancing information based on user input to the user interface. The portfolio management server 310 may receive transaction information about virtual assets included in the portfolio from the exchange server 330 at set intervals. The portfolio management server 310 may determine market health using the database 350 based on transaction information received at each set cycle. The portfolio management server 310 receives transaction information about virtual assets from the exchange server 330 and generates a plurality of evaluation scores through a neural network using the database 350 based on the transaction information about virtual assets. can do. Here, transaction information about virtual assets may include information about off-chain transactions in which cryptocurrency is traded on an exchange, rather than information about on-chain transactions recorded in the distributed ledger of the cryptocurrency. The portfolio management server 310 may rebalance the portfolio using the database 350 based on the plurality of evaluation scores.

The user terminal 320 may include all types of devices including a function for displaying an image screen and a user input interface. For example, the user terminal 320 may include a smartphone, tablet PC, PC, smart TV, mobile phone, personal digital assistant (PDA), laptop, media player, micro server, global positioning system (GPS) device, e-book reader, It may include digital broadcasting terminals, navigation systems, kiosks, MP3 players, digital cameras, home appliances, and other mobile or non-mobile computing devices. Additionally, the user terminal 320 may include wearable devices such as watches, glasses, hair bands, and rings equipped with a display function and a user input interface. For example, the user terminal 330 may include the electronic device 101 of FIG. 1 .

The exchange server 330 may be a server that provides an interface related to transactions for virtual assets and manages transactions for virtual assets. For example, the exchange server 330 may transmit transaction information about virtual assets to the portfolio management server 310 or the user terminal 320 through the network 340. When the portfolio management server 310 or the user terminal 320 completes the authentication process with the exchange server 330, the exchange server 330 sends transaction information about the virtual asset to the portfolio management server 310 or the user terminal 320. It can be transmitted through the network 340. For example, exchange server 330 may include server 108 of FIG. 1 .

As shown in FIG. 3 , components of the system 30 that performs rebalancing on a portfolio of virtual assets may be connected through a network 340 . According to one embodiment, a network refers to a connection structure that allows information exchange between nodes such as a plurality of terminals and servers. Examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, and LTE ( Long Term Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area) Network), PAN (Personal Area Network), Bluetooth network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc., but are not limited thereto.

Meanwhile, in the virtual asset market, sell orders and buy orders are formed based on the prices desired by sellers and buyers, respectively, and the market price is formed as a result of mutual agreement. The more active the market is, the more sell and buy orders are placed at a price close to the agreed upon price, resulting in transactions being concluded at a price that is less different from the market price. However, when the market is less active, the desired price can be greatly reduced due to insufficient order volume. A transaction may be concluded at a price that is out of line. Taking advantage of this, various attempts have been made to make it appear as if market transactions are actively taking place even when they are not, and these attempts have caused unexpected losses to service users. In particular, abnormal attempts are most often made by exploiting the fact that cryptocurrency exchanges only display the price fluctuation range and trading volume of cryptocurrency, and it is difficult for service users to identify abnormal attempts until they continuously observe changes in the quoted price. . In response, the portfolio management server 310 according to the present disclosure measures changes in quotes submitted in the market, identifies and quantifies the normal range of price volatility that can occur based on the trading volume in the market, and quantifies the normal range of price volatility. Based on this, rebalancing can be performed on the portfolio.

If the quote submitted in the cryptocurrency trading market is a price formed only through normal transactions, it shows various patterns during the conclusion process. Specifically, in the case of execution by market order, if the first quantity of the first bid price concluded is greater than the trading volume, a quote equal to the first quantity minus the trading volume remains. In the case of execution by limit price order, if the first quantity is smaller than the trading volume and the limit price is not the price at which the second quote will be executed, the price equal to the trading volume minus the first quantity remains as the price on the other side, and the limit price is higher than the second price. In the case of the price at which the contract is to be executed, an quotation equal to the quantity of the difference from the second quotation remains. In other words, a change in the quote price occurs along with the transaction volume due to a single execution order. If this is quantified, it is predicted how much the submitted quote price will be executed and how much the quote price will change for the execution order corresponding to the average value of the transaction volume. It can be. Using this, the portfolio management server 310 according to the present disclosure can calculate an indicator through average calculation and deviation calculation with respect to the range of possible change measured during a specific time period in consideration of transaction volume and fluctuation range.

The portfolio management server 310 can generate an ideal indicator by determining the price change when a transaction occurs for all transactions for each index constituent item and calculating the deviation thereof. However, abnormal indicators are highly prone to errors when there is abnormal market disturbance. In order to consider price changes due to abnormal behavior, the portfolio management server 310 calculates the deviation by adding the price change when a transaction occurs and the price change that may occur, including the quantity canceled after the quote is submitted within the price change section, to calculate the deviation. (blink) A reflection indicator can be created. Alternatively, the portfolio management server 310 may generate a general indicator by measuring the quote price multiple times for each price change section and calculating the deviation of the difference between the effective ask price and the current price within the price change section.

The generated indicators use a method of setting the baseline for the next section based on the statistics of the previous section, so abnormal behavior that deviates from the average value is reflected in the form of noise. In other words, if a deviation in volatility that is excessively larger or smaller than the general volatility is observed, the indicator is immediately reflected in the form of noise.

In addition, since the indicator is an indicator that derives the deviation of the measurement results of each section, the larger the number of samples, the more accurate the result. Therefore, the reliability of the indicator can be increased when multiple measured results are adopted when multiple nodes form a network and each generate and accumulate results.

The portfolio management server 310 can extract index transaction data appropriate for the current market situation from transaction information and perform rebalancing of the portfolio based on investment information related to transaction volume and fluctuation range. Below, a specific method by which the portfolio management server 310 performs rebalancing on a portfolio is illustrated.

Figure 4 shows a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment. The embodiment of FIG. 4 can be combined with various embodiments of the present disclosure.

Referring to FIG. 4, in step S401, the portfolio management server may receive portfolio information about virtual assets from the user terminal. Portfolio information about virtual assets may include information about trading items, number of holdings, date when the transaction was concluded, and exchange.

For example, portfolio information about virtual assets may include authentication information about the exchange where the user terminal entered into a transaction. Here, the authentication information may include at least one of an ID related to the user terminal, an authentication number, or biometric information for authentication.

For example, the portfolio management server may request portfolio information about virtual assets from the user terminal and receive portfolio information about virtual assets from the user terminal.

In step S402, the portfolio management server may obtain transaction information on trading items included in the portfolio information for each exchange at every cycle set in the portfolio management server.

For example, the portfolio management server may determine trading items based on portfolio information and obtain transaction information for each exchange for the trading items at a cycle set in the portfolio management server. Here, the trading item related to the portfolio information may be an item for a virtual asset traded by the user. That is, the portfolio management server can request transaction information for each exchange for trading items included in the portfolio information at a period set in the portfolio management server, and receive transaction information from each exchange server. At this time, the portfolio management server may complete the authentication process with the exchange server based on the authentication information and then receive transaction information about the trading items included in the portfolio information from the exchange server.

The cycle of acquiring transaction information on trading items included in the portfolio information from the exchange server may be preset in the portfolio management server. For example, the period can be set to 5 minutes, 3 minutes, 1 minute or 30 seconds. The period can be adjusted according to the frequency of the preset words. Here, the frequency of the preset word may be determined based on text data collected through web crawling performed by the portfolio management server. For example, preset words can be first words that indicate positive signals about the current market, such as ‘good news’, ‘up’, ‘boom’, etc., and negative connotations such as ‘bad news’, ‘down’, ‘recession’. It may include a second word with . At this time, the preset word may be a word located within a preset text range from the position of the name of the trade item included in the portfolio in a sentence in which the trade item is searched.

Additionally, according to one embodiment, the portfolio management server provides transaction information about trading items included in the portfolio information according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling. You can change the period of obtaining from the exchange server.

In step S403, the portfolio management server may extract data on a plurality of first variables based on transaction information about the transaction item obtained for each cycle. The plurality of first variables may include market capitalization, transaction execution price, sell price, buy price, sell price section, buy price section, execution transaction volume for each section, order volume for each section, and cancellation transaction volume for each section. Here, the market capitalization is the amount of supply of virtual assets in circulation for the relevant trading item multiplied by the price of a single unit. The transaction execution price is the price at which the transaction for the relevant transaction item is concluded. The ask price is the price set by the seller to sell the item. The bid price is the price set by the buyer to purchase the relevant trading item. The ask price range is the gap between different ask prices. The bid price range is the gap between different bid prices. The transaction volume concluded by section is the volume of transactions concluded in the section of the sell price and the section of the buy price. The order volume by section is the amount of orders submitted to the exchange in the sell price section and the buy price section. Canceled transaction volume by section is the volume of transactions canceled after orders were submitted to the exchange in the ask price section and the buy price section.

For example, when there are multiple transaction items, data on the plurality of first variables may be extracted for each transaction item.

In step S404, the portfolio management server may determine market health for each cycle based on data on the plurality of first variables.

For example, market health is determined based on the price change value including the trading volume canceled after a transaction was ordered on the exchange within the cycle, the first change value determined based on the actual price change value within the cycle, and the valid quote price within the cycle. It may be determined according to a second change value determined based on the value minus the price within the cycle.

For example, market health can be determined by Equation 1 below.

In Equation 1, s is the market health, N is the transaction volume that occurred during the period, c is a weight according to the market capitalization of the transaction item, and M _ai is the weight for each of the N transactions. It is the sum of the price changes including the transaction volume canceled after the transaction was ordered on the exchange, M _bi is the sum of the actual price changes for each of the N transactions, and P _vi is the N It is a value that is the sum of valid quotes for each of the N transactions, where P _ri is a value that is the sum of the execution prices for each of the N transactions, and the P _d may be a default value for each of the N transactions.

The weight according to the market capitalization of the relevant trading item may be determined according to the ratio of the market capitalization of the relevant trading item and a preset standard value. The preset reference value may be determined based on the average market capitalization of virtual assets currently traded on the exchange, the period during which the virtual asset has been traded, and the number of mined virtual assets. For example, the weight according to the market capitalization of the relevant trading item may be determined between 0 and 2.

The effective quote price may be the price expected when a transaction is concluded at a market price equal to the average transaction volume. Here, the market price is the price that can be sold immediately at the current time. For example, the effective quote price may be a price determined based on the transaction volume and average transaction volume for each section at the time of transaction occurrence.

The P _d may be preset in the portfolio management server.

For example, the larger the weight applied to the market capitalization is the sum of the price change reflecting the transaction volume canceled after a transaction was ordered and the actual price change, the smaller the market health is determined, and the effective quote price is determined to be smaller. The larger the value obtained by subtracting the execution price from the weight applied to the market capitalization, the smaller the market health is determined, so the portfolio management server effectively improves the health of the market by considering the impact of the cryptocurrency market on the range of price fluctuations. You can judge.

Additionally, the preset threshold may be adjusted according to the frequency of the preset word. For example, the portfolio management server may change the preset threshold value according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling.

In step S405, the portfolio management server determines the transaction period from the time the user holds the virtual asset to the time the market health decreases below the preset threshold, based on the market health being below the preset threshold. Data on a plurality of second variables can be extracted from transaction information about the transaction item.

For example, if the user has multiple virtual assets, if the market health for at least one of the multiple virtual assets is below a preset threshold, the portfolio management server For each virtual asset, data on a plurality of second variables can be extracted for the trading period from the time the virtual asset is held to the time the market health decreases below the preset threshold.

Or, for example, if the user has multiple virtual assets and the average value of the market health for the multiple virtual assets is below a preset threshold, the portfolio management server For each of a plurality of virtual assets, data on a plurality of second variables may be extracted for the trading period from the time the virtual asset is held to the time the market health decreases below the preset threshold.

Here, the plurality of second variables are, for the trading period, the total return, the average return per transaction for profitable transactions, the average return per transaction for loss-generating transactions, and the return for profitable transactions. It can include standard deviation, standard deviation of loss rate for losing trades, total number of trades, and win percentage.

For example, the total return may be the current value of the virtual asset, that is, the appraised amount minus the initial value of the virtual asset (investment principal) divided by the principal of the initial equity value. The win rate may be the probability of generating a profit per transaction. For example, the win rate may be the number of profitable trades divided by the total number of trades. The average return per trade for profitable trades can be determined based on the win rate and the average return per trade. The average return per trade for a losing trade can be determined based on 1 minus the win rate and the average loss rate per trade.

In step S406, the portfolio management server may determine a plurality of evaluation scores through an evaluation model using a neural network based on data on the plurality of second variables.

Here, the evaluation score is a first value applied with a first weight to the standard deviation of the rate of return for transactions that generated profit within the period and a second value applied with a second weight to the standard deviation of the loss rate for transactions with a loss within the period. It may be the sum of the divided value from the average annual rate of return for the above period. At this time, the first weight may be a smaller value than the second weight.

For example, the neural network may include an input layer, one or more hidden layers, and an output layer. Each learning data consisting of data for a plurality of variables and a plurality of evaluation scores of the correct answer is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector, and the output vector is It is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each training data, and the parameters of the neural network are It can be learned in a way that the loss value becomes smaller.

For example, multiple evaluation scores can be determined by trading time interval, trading algorithm, trading item, and exchange.

The plurality of evaluation scores may be determined for each transaction time interval for a plurality of trading algorithms. Here, the plurality of trading algorithms include a first algorithm in which transactions are concluded based on the standard deviation for the price fluctuation section determined based on the Blink reflection indicator, a second algorithm in which transactions are concluded based on a preset moving average, and the current As a standard, a third algorithm may be included in which transactions are concluded according to the average value of the change range of candles for the previous positive and negative candles. Here, the blink reflection indicator may be an indicator that calculates the deviation by adding the price change when a transaction occurs and the price change that may occur, including the quantity canceled after the quote is submitted within the price change range. For example, the trading algorithm may automatically conclude a transaction when certain conditions are met, and may have different trading algorithms depending on the specific conditions. Here, transaction time intervals may include 15 minutes, 1 hour, 4 hours, and 24 hours. In other words, a plurality of trading algorithms can determine whether certain conditions for executing a transaction are satisfied at each set trading time interval. Without being limited to the present disclosure regarding the above transaction time intervals, a larger number of transaction time intervals may be set. Through this, the portfolio management server can determine evaluation scores for cases where transactions are performed at each trading time interval for different trading algorithms based on data on a plurality of variables.

The plurality of transaction algorithms can be set for each virtual asset. For example, if the virtual assets held by the user are Bitcoin and Ethereum, the plurality of transaction algorithms may be set for each of Bitcoin and Ethereum, and an evaluation score for Bitcoin and an evaluation score for Ethereum For multiple trading algorithms, evaluation scores can be determined for each distance and time interval.

Each of the above virtual assets can be set for each exchange. For example, evaluation scores may be determined for Bitcoin and Ethereum on exchanges other than the exchange where the user entered into the transaction. In other words, the evaluation scores for Bitcoin and Ethereum on Exchange A can be determined for each distance time interval for multiple trading algorithms, and the evaluation scores for Bitcoin and Ethereum on Exchange B can be determined for multiple trading algorithms. It can be determined for each distance and time interval.

In step S407, the portfolio management server may perform rebalancing of the portfolio based on the plurality of evaluation scores.

Here, rebalancing of the portfolio can be performed according to the proportion of virtual assets. For example, if the virtual assets held by the user are Bitcoin and Ethereum, rebalancing the portfolio can be performed based on the proportion of Bitcoin and the proportion of Ethereum.

For example, the proportion of the virtual asset may be determined based on the number of transactions per day, the expected profit/loss ratio per transaction, and the plurality of evaluation scores. The number of transactions per day may be the total number of transactions divided by the transaction period. The expected profit/loss ratio per transaction can be determined based on the win rate within the transaction period, the average return per transaction for profitable transactions within the transaction period, and the average loss rate per transaction for transactions with losses within the transaction period. there is.

For example, the proportion of the most assets can be determined by Equation 2 below.

In Equation 2, the Cap is the proportion of the virtual asset, the Trade per Day is the number of times the virtual asset is traded per day, and the Expect P&L is the expected profit/loss ratio per transaction for the virtual asset, The TSVS may be a comprehensive evaluation score for the virtual asset, n may be the number of transaction items, and the TSVS _i may be a comprehensive evaluation score for the ith transaction item.

Here, the Trade per Day may be the total number of transactions divided by the trading period. Here, the Expect P&L may be determined based on the win rate within the trading period, the average return per transaction for profitable transactions within the trading period, and the average return per transaction for transactions with loss within the trading period. Here, the comprehensive evaluation score may be a score determined based on a plurality of evaluation scores determined for the virtual asset. For example, the comprehensive evaluation score may be a weighted average value that reflects the weight of the rebalancing criteria in a plurality of evaluation scores.

Through this, the portfolio management server can perform rebalancing of the portfolio according to the characteristics of virtual assets by considering various factors such as trading algorithms, transaction time intervals, and exchanges related to virtual assets.

For example, Expect P&L for the virtual asset can be determined by Equation 3 below.

In Equation 3, Expect P&L is the expected profit/loss ratio per transaction, and Winr is the win rate for the transaction period. The WT ProfitAvg may be the average return per transaction for a profitable transaction within the trading period, and the LT ProfitAvg may be the average loss rate per transaction for a loss-generating transaction within the trading period.

Unlike the Sharpe index used in the existing stock market, the evaluation score can be determined through the Sharpe index modified into a form suitable for evaluating algorithms for virtual assets. In most assets, there may be a large deviation in the return rate of the algorithm for virtual assets due to transactions that generate large profits, which is inevitable due to the market characteristics of virtual assets. Therefore, to assess risk, new weights may be needed to focus on the deviation when a loss occurs, rather than the deviation when a profit is made.

For example, the evaluation score may be determined by Equation 4 below.

In Equation 4, the StrategyValueScore is the evaluation score, the Total Profit is the total return, the TradingDay is the trading period, and the Profit sd(+) is the standard of return for transactions that generated profit within the trading period. It is a deviation, and the Profit sd(-) may be the standard deviation of the loss rate for transactions in which losses occurred within the trading period.

Additionally, for example, if only one virtual asset is included in the portfolio, the message requesting rebalancing may further include a value for the rebalancing criterion selected by the user.

Or, for example, if only one virtual asset is included in the portfolio, the server may randomly select a value for the rebalancing criterion.

If the value for the rebalancing standard corresponds to a trading algorithm, the portfolio management server may determine an evaluation score for each trading time interval for a plurality of trading algorithms for the one asset. The portfolio management server can set evaluation scores for each trading time interval for the plurality of trading algorithms for each exchange. Through this, the portfolio management server can determine the weight for each of the plurality of trading algorithms. In addition, if the value for the rebalancing standard corresponds to a trading time interval, the portfolio management server can set the evaluation score for each trading algorithm for each exchange for the plurality of trading time intervals, and the portfolio management server can set the evaluation score for each exchange for the plurality of trading time intervals. The proportion can be determined. In addition, for example, if the value for the rebalancing standard corresponds to an exchange, the portfolio management server can set the evaluation score for each trading algorithm for the plurality of exchanges by trading time interval, and the portfolio management server can set the evaluation score for each trading algorithm for the plurality of exchanges based on the exchange. You can determine the proportion on the exchange.

Figure 5 is a flowchart of a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment. The embodiment of FIG. 5 can be combined with various embodiments of the present disclosure.

Referring to FIG. 5, in step S501, the portfolio management server may receive portfolio information about virtual assets from the user terminal. For example, authentication information may be included in portfolio information for virtual assets.

In step S502, the portfolio management server may determine whether the portfolio information includes authentication information. Authentication information may include at least one of an ID related to the user terminal, an authentication number, or biometric information for authentication. Here, biometric information is biometric information that can identify the user, and may include at least one of information about the user's fingerprint, information about the user's iris, or information about the user's face.

In step S503, based on the fact that the portfolio information includes authentication information, the portfolio management server may receive transaction information on trading items included in the portfolio information from the exchange server at every cycle set in the portfolio management server. Here, the trading items included in the portfolio information may be items for virtual assets traded by the user.

For example, after completing the authentication process for each exchange server based on the authentication information, the portfolio management server can receive transaction information about the trading items included in the portfolio information from each exchange server at the cycle set in the portfolio management server. there is. That is, the portfolio management server can receive transaction information on trading items included in the portfolio information for each exchange at a period set in the portfolio management server.

For example, when there are multiple trading items, the portfolio management server can receive transaction information for each of the multiple trading items for each exchange.

In step S504, based on the portfolio information not including authentication information, the portfolio management server crawls the web for a plurality of exchange servers to retrieve transaction information about the trading items included in the portfolio information at a period set in the portfolio management server. It can be obtained at each exchange.

For example, when there are multiple trading items, the portfolio management server can obtain transaction information for each of the multiple trading items for each exchange.

Additionally, for example, the portfolio management server exchanges transaction information on trading items included in the portfolio information according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling. You can change the acquisition cycle from the server. Here, web crawling may be performed on a plurality of websites related to virtual assets and a plurality of websites related to news.

For example, if the frequency of the first word divided by the sum of the frequencies of the first word and the frequency of the second word is 0.7 or more, the period may be set to 5 minutes. For example, if the frequency of the first word divided by the sum of the frequencies of the first word and the second word is less than 0.7 and more than 0.5, the period may be set to 3 minutes. For example, if the frequency of the first word divided by the sum of the frequencies of the first word and the second word is less than 0.5 and more than 0.3, the period may be set to 1 minute. For example, if the frequency of the first word divided by the sum of the frequencies of the first word and the second word is less than 0.3, the period may be set to 30 seconds.

Therefore, the portfolio management server can more effectively determine market health by adaptively changing the cycle of acquiring transaction information according to issues related to virtual assets.

In step S505, the portfolio management server may extract data on a plurality of first variables based on transaction information about the transaction item obtained for each cycle. The portfolio management server may determine market health for each cycle based on data on the plurality of first variables.

In step S506, the portfolio management server may determine whether the market health is below a preset threshold.

For example, if a user holds multiple virtual assets, the portfolio management server may determine whether the market health of at least one of the multiple virtual assets is below a preset threshold.

Or, for example, if the user holds multiple virtual assets, the portfolio management server may determine whether the average value of market health for the multiple virtual assets is below a preset threshold.

Additionally, for example, the portfolio management server may change the preset threshold according to the ratio of the frequency count of the first word and the frequency count of the second word collected through web crawling.

Additionally, for example, if the frequency number of the first word divided by the sum of the frequency numbers of the first word and the frequency number of the second word is greater than or equal to 0.7, the preset threshold value will be set as the minimum threshold value. You can. For example, if the frequency count of the first word divided by the sum of the frequency counts of the first word and the frequency count of the second word is less than 0.7 and more than 0.5, the preset threshold value is the next largest value after the minimum threshold value. It may be set to the first threshold. For example, if the frequency count of the first word divided by the sum of the frequency counts of the first word and the frequency count of the second word is less than 0.5 and more than 0.3, the preset threshold is the next largest value after the first value. It may be set as the second threshold. For example, if the frequency count of the first word divided by the sum of the frequency counts of the first word and the frequency count of the second word is less than 0.3, then the preset threshold is the maximum threshold that is the next larger value after the second threshold. Can be set to any value.

Accordingly, the portfolio management server can set different conditions for performing portfolio rebalancing by adaptively changing the threshold value related to market health according to issues related to virtual assets.

In step S507, if the market health is greater than the preset threshold, the portfolio management server may determine whether to receive a rebalancing request message. Here, the rebalancing request message is a message transmitted from the user terminal to the portfolio management server and may be a message requesting rebalancing of the portfolio for virtual assets.

In step S508, the portfolio management server stores data on a plurality of second variables for the trading period from the time the user holds the virtual asset to the time the market health decreases below the preset threshold for the trading item. It can be extracted from transaction information.

In step S509, the portfolio management server may determine a plurality of evaluation scores through an evaluation model using a neural network based on data on the plurality of second variables.

In step S510, the portfolio management server may determine whether there are multiple trading items included in the portfolio.

In step S511, when there are multiple trading items included in the portfolio, the portfolio management server may determine the proportion of virtual assets to the portfolio based on the comprehensive evaluation score. For example, the portfolio management server can determine the proportion of virtual assets included in the portfolio using Equation 2 described above.

Here, the comprehensive evaluation score is weighted by applying the first standard weight for the trading time interval, the second standard weight for the trading algorithm, the third standard weight for the exchange, and the fourth standard weight for the trading item to the plurality of evaluation scores. It may be an average value. The standard weight may be a weight applied to the evaluation score determined for each rebalancing standard. For example, if the first standard weight for the trading time interval is applied, when determining the evaluation score for Bitcoin among the trading items included in the portfolio, the first standard weight will be applied to the evaluation score determined for each trading time interval. You can. The first to fourth reference weights may be preset in the portfolio management server. For example, the first to fourth reference weights may be preset in the portfolio management server by the user terminal. Accordingly, the portfolio management server can rebalance the portfolio by reflecting the user's desired investment direction.

Or, for example, the portfolio management server may randomly determine the first to fourth reference weights.

In step S512, when there is one trading item included in the portfolio, the portfolio management server may determine the proportion of virtual assets in the portfolio based on the value for the rebalancing standard.

For example, the value for the rebalancing standard may be included in portfolio information for a virtual asset or a rebalancing request message. At this time, the portfolio management server replaces the comprehensive evaluation score in Equation 2 above with the evaluation score for the rebalancing standard based on the value for the rebalancing standard, and replaces the number of traded items with the number related to the rebalancing standard, , the overall evaluation score for the ith trading item can be replaced with the evaluation score for the ith rebalancing standard. That is, for example, if the value for the rebalancing standard corresponds to a trading algorithm, the portfolio management server uses Equation 2 described above, but calculates the overall evaluation score as the evaluation score for the trading algorithm currently set by the user terminal. By substituting, replacing the number of trading items with the number of trading algorithms, and substituting the overall evaluation score for the i-th trading item with the evaluation score for the i-th trading algorithm, the weight for the trading algorithm can be determined.

In step S513, the portfolio management server may perform rebalancing on the portfolio based on the proportion of virtual assets to the portfolio.

Figure 6 is an example of an evaluation model according to one embodiment. The embodiment of FIG. 6 can be combined with various embodiments of the present disclosure.

Referring to FIG. 6, the neural network used in the evaluation model may be a multivariate long short term memory networks (LSTM) model. In general, RNN (recurrent neural network) can effectively model time-series information because hidden layer values for existing inputs stored internally are considered in the output for the next input value. However, since RNN is a structure that depends on past observation values, problems may occur where the gradient is vanishing or the gradient has a very large value (exploding gradient). The model to solve this problem is LSTM, and by replacing the nodes inside the LSTM with memory cells, it is possible to accumulate information or delete part of past information, and can complement the problem of the RNN.

For example, a neural network may include an input layer 610, one or more hidden layers 620, and an output layer 630.

For example, the one or more hidden layers 620 include one or more LSTM blocks, and one LSTM block includes a memory cell, an input gate, a forget gate, and an output gate ( output gate).

For example, the memory cell is a node that outputs a result through an activation function, and the memory cell can perform a recursive operation that uses the value output from the memory cell at the previous point as its input at the current point. You can. For example, when the current time point is t, the value output by a memory cell at the current time point t may be influenced by the values of past memory cells. A memory cell can output a cell state (C _t ) value and a hidden state (h _t ) value. In other words, the memory cell uses the cell state value (C _t-1 ) and hidden state value (h _t-1 ) delivered by the memory cell at time t-1 as input values for calculating the cell state value and hidden state value at time t. It can be used as

For example, the input gate 622, the delete gate 621, and the output gate 623 all include a sigmoid layer, and may indicate how much information input is transmitted through the sigmoid layer. For example, a sigmoid layer uses a sigmoid function ( ) may be a layer that is an activation function. Additionally, for example, the cell state 624 is controlled through the input gate 622, the delete gate 621, and the output gate 623, and weights may exist for each gate and input.

For example, data for a plurality of second variables may be vectorized through data preprocessing. That is, data for a plurality of second variables can be converted into a plurality of input vectors consisting of an input vector for each transaction time interval, an input vector for each trading algorithm, an input vector for each trading item, and an input vector for each exchange.

For example, a plurality of input vectors are input to the input layer, and the deletion gate generates h _t-1 (hidden state at time t-1) and x _t (input value at time t) based on the input vectors. ), values between 0 and 1 can be transmitted to C _t-1 . Here, the value between 0 and 1 is the amount of information that has gone through the deletion process. The closer it is to 0, the more information is deleted, and the closer it is to 1, the more complete information can be transmitted.

For example, the input gate 622 may determine the value to be updated through the sigmoid layer, the tanh layer may generate a C _t vector that is new candidate values, and store the C t vector in the cell state 624. tanh stands for nonlinear activation function (hyperbolic tangent function).

For example, by updating the past cell state, C _t-1 , a new cell state, C _t , can be created. That is, for the cell state 624, information may be deleted by multiplying the cell state by f _t , and a scaled value of the update value may be added.

For example, the output gate 623 may determine a portion of the cell state to be output based on a plurality of input vectors in the sigmoid layer, and the output gate 623 may tanh the cell state determined in the sigmoid layer. Through the layer, you can multiply the output value with a value between -1 and 1.

For example, the evaluation model may be an LSTM model in which the deletion gate 621 and the input gate 622 are combined. In this case, the calculation can be performed more quickly by deleting only the old information to which new information is added.

Accordingly, the portfolio management server can use the parameters of the neural network learned through the evaluation model, and the portfolio management server considers the preset criteria (trading time interval, trading algorithm, trading item, and exchange) to meet each criterion. An evaluation score can be determined.

Figure 7 is a block diagram showing the configuration of a portfolio management server according to an embodiment. One embodiment of FIG. 7 may be combined with various embodiments of the present disclosure.

As shown in FIG. 7, the portfolio management server 700 may include a processor 710, a communication unit 720, and a memory 730. However, not all of the components shown in FIG. 7 are essential components of the portfolio management server 700. The portfolio management server 700 may be implemented with more components than those shown in FIG. 7, or the portfolio management server 700 may be implemented with fewer components than those shown in FIG. 7. For example, the portfolio management server 700 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 710, the communication unit 720, and the memory 730. It may be possible.

The processor 710 typically controls the overall operation of the portfolio management server 700. The processor 710 may include one or more processors and control other components included in the portfolio management server 700. For example, the processor 710 can generally control the communication unit 720 and the memory 730 by executing programs stored in the memory 730. Additionally, the processor 710 may perform the functions of the portfolio management server 700 shown in FIGS. 3 to 7 by executing programs stored in the memory 730.

The communication unit 720 may include one or more components that allow the portfolio management server 700 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as the portfolio management server 700 or a sensing device, but is not limited thereto. The communication unit 720 may receive a user input from another electronic device or receive data stored in an external device from an external device through a network.

For example, the communication unit 720 may transmit and receive a message to establish a connection with at least one device. The communication unit 720 may transmit information generated by the processor 710 to at least one device connected to the server. The communication unit 720 may receive information from at least one device connected to the server. The communication unit 720 may transmit information related to the received information in response to information received from at least one device.

The memory 730 may store programs for processing and control of the processor 710. For example, the memory 730 may store information input to a server or information received from another device through a network. Additionally, the memory 730 may store data generated by the processor 710. The memory 730 may store information input to or output from the portfolio management server 700.

The memory 730 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.), and RAM. (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , and may include at least one type of storage medium among optical disks.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (3)

In a method for a portfolio management server to rebalance a portfolio of virtual assets using a neural network,
Receiving portfolio information about virtual assets from a user terminal;
Obtaining transaction information on transaction items included in the portfolio information for each exchange at a period set in the portfolio management server;
extracting data on a plurality of first variables based on transaction information about the transaction item obtained at each cycle set in the portfolio management server;
The plurality of first variables include market capitalization, transaction execution price, sell price, buy price, sell price section, buy price section, transaction volume for each section, order volume for each section, and cancellation transaction volume for each section,
determining market health at each cycle set in the portfolio management server based on data on the plurality of first variables;
Based on the market health being below the preset threshold, data for a plurality of second variables for the trading period from when the user holds the virtual asset to the time when the market health decreases below the preset threshold. extracting from transaction information about the transaction item;
The plurality of second variables are, for the trading period, the total return, the average return per transaction for profitable transactions, the average return per transaction for loss-generating transactions, and the standard return for profitable transactions. Deviation, standard deviation of loss rate for losing trades, total number of trades and win percentage;
determining a plurality of evaluation scores through an evaluation model using a neural network based on data on the plurality of second variables; and
Including performing rebalancing of the portfolio based on the plurality of evaluation scores,
Each of the plurality of evaluation scores is determined by Equation 1 below for each transaction time interval, transaction algorithm, and exchange,

In Equation 1, the StrategyValueScore is the evaluation score, the Total Profit is the total return, the TradingDay is the trading period, and the Profit sd(+) is the standard deviation of returns for transactions that generated profits within the trading period. , and the Profit sd(-) is the standard deviation of the loss rate for transactions that incurred losses within the trading period,
Rebalancing of the portfolio is performed according to the proportion of virtual assets,
The proportion of the virtual asset is determined based on the number of transactions per day, the expected profit/loss ratio per transaction, and the plurality of evaluation scores,
The number of transactions per day is the total number of transactions divided by the transaction period,
The expected profit/loss ratio per transaction is determined based on the win rate within the transaction period, the average return per transaction for profitable transactions within the transaction period, and the average loss rate per transaction for transactions that incurred loss within the transaction period. ,
The market health is determined by Equation 2 below,

In Equation 2, s is the market health, N is the transaction volume that occurred during the period, c is a weight according to the market capitalization of the transaction item, and M _ai is the weight for each of the N transactions. It is the sum of the price changes including the transaction volume canceled after the transaction was ordered on the exchange, M _bi is the sum of the actual price changes for each of the N transactions, and P _vi is the N is the sum of valid quotes for each of the N transactions, where P _ri is the sum of the execution prices for each of the N transactions, and P _d is the default value for each of the N transactions,
The weight according to the market capitalization of the relevant trading item is determined according to the ratio of the market capitalization of the trading item and the preset standard value,
The preset reference value is determined according to the average market capitalization of virtual assets currently traded on the exchange, the period during which the virtual asset was traded, and the number of mined virtual assets,
The valid quote price is determined based on the transaction volume and average transaction volume for each section at the time of transaction occurrence,
The frequency of preset words is determined based on text data collected through web crawling performed by the portfolio management server,
The cycle set in the portfolio management server is adjusted according to the frequency of the preset word,
the preset threshold is adjusted according to the frequency of the preset word,
The cycle set in the portfolio management server is applied at the same cycle to each exchange.
method.
According to clause 1,
The neural network includes an input layer, one or more hidden layers, and an output layer,
Each learning data consisting of data for a plurality of variables and a plurality of evaluation scores of the correct answer is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector, and the output vector is It is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each training data, and the parameters of the neural network are Learning in the direction of decreasing loss value,
method.

delete

Images