KR102568752B1 - Method and apparatus for rebalancing on specific data using a neural network - Google Patents

Abstract

Embodiments suggest a method and apparatus for a portfolio management server to perform rebalancing on a portfolio of virtual assets using a neural network. In the method according to an embodiment, a first message requesting rebalancing is received from a user terminal, the first message includes first portfolio information on virtual assets owned by the user, and the first message is received. Based on this, transaction information on the trading item related to the first portfolio information is acquired for each exchange, and the time when the user holds the virtual asset based on the transaction information on the trading item and the time when the first message is received Data on a plurality of variables is extracted for the trading period up to, and the plurality of variables are, for the trading period, total return, average return per trade for profitable trades, and trades for losses. It includes the average rate of return per transaction, the standard deviation of the rate of return for profitable transactions, the standard deviation of the loss rate for lost transactions, the total number of transactions and the winning rate, and using a neural network based on the data on the plurality of variables. A plurality of evaluation scores are determined through an evaluation model, rebalancing information for the first portfolio is determined based on the plurality of evaluation scores, and a second message including the rebalancing information for the first portfolio is transmitted. and performing rebalancing on the first portfolio based on the rebalancing information based on transmission to a user terminal and receiving a rebalancing approval message from the user terminal. The evaluation score is a value greater than the first value obtained by applying a first weight to the standard deviation of returns for transactions in which profits occurred within the trading period and a value greater than the first weight to the standard deviation of loss rates for transactions in which losses occurred within the trading period. It may be a value obtained by dividing a value obtained by summing the second values to which the second weight having the second weight is applied is divided by the annual average rate of return for the trading period.

Description

Method and apparatus for performing rebalancing on specific data using a neural network

Embodiments of the present disclosure relate to a technology of rebalancing a portfolio of virtual assets, and to a technology of performing rebalancing of a portfolio of virtual assets using a neural network.

On the other hand, although the virtual asset market such as cryptocurrency has grown rapidly, there is a lack of asset management methods that consider the characteristics of virtual assets, only using asset management methods in the existing stock market for the rapidly growing virtual asset market.

In particular, it can be difficult to manage a portfolio for cryptocurrencies using techniques used in the stock market, since there is no suitable sample that can be set as a benchmark in the cryptocurrency market, and the variation in returns is wide compared to the existing stock market. there is.

Therefore, it is necessary to rebalance the existing cryptocurrency portfolio into a portfolio with the lowest risk versus profitability through an evaluation model and a prediction model using a neural network based on transaction data using indexes suitable for the cryptocurrency market. .

Embodiments of the present disclosure may provide a method and apparatus for performing rebalancing on a portfolio of virtual assets using a neural network.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

A method for a portfolio management server to perform rebalancing on a portfolio of virtual assets using a neural network according to an embodiment includes receiving a first message requesting rebalancing from a user terminal; , The first message includes first portfolio information on virtual assets held by the user, and based on receiving the first message, transaction information on trading items related to the first portfolio information is obtained for each exchange, , Based on the transaction information for the transaction item, data for a plurality of variables is extracted for a transaction period from the time the user holds the virtual asset to the time the first message is received, the plurality of variables, For the trading period, the total return, the average return per trade on profitable trades, the average return per trade on lossy trades, the standard deviation of returns on profitable trades, and the loss ratio on losing trades. A standard deviation of, including a total number of transactions and a win rate, determining a plurality of evaluation scores through an evaluation model using a neural network based on data on the plurality of variables, and determining the first evaluation score based on the plurality of evaluation scores. Based on determining rebalancing information for a portfolio, transmitting a second message including rebalancing information for the first portfolio to the user terminal, and receiving a rebalancing approval message from the user terminal, and performing rebalancing on the first portfolio based on the rebalancing information. The evaluation score is a value greater than the first value obtained by applying a first weight to the standard deviation of returns for transactions in which profits occurred within the trading period and a value greater than the first weight to the standard deviation of loss rates for transactions in which losses occurred within the trading period. It may be a value obtained by dividing a value obtained by summing the second values to which the second weight having the second weight is applied is divided by the annual average rate of return for the trading period.

For example, the rebalancing information for the first portfolio may include weights for virtual assets. The weight 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 a value obtained by dividing the total number of transactions by the transaction period. The expected profit/loss rate per transaction may be determined based on the win rate within the trading period, the average rate of return per transaction for profitable transactions within the trading period, and the average loss rate per transaction for transactions with losses within the trading period. there is.

According to an 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 rate of return, the TradingDay is the trading period, the Profit sd (+) is the standard deviation of the rate of return for transactions generating profits within the trading period, , The Profit sd(-) may be the standard deviation of the loss rate for trades in which losses occur during the trading period.

According to an embodiment, the neural network may include an input layer, one or more hidden layers, and an output layer. Each learning data composed of data on a plurality of variables and a plurality of evaluation scores of correct answers 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 The input is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value by using a loss function that compares the output vector with the correct answer vector for each learning data. It can be learned in a direction in which the loss value becomes smaller.

For example, the plurality of evaluation scores may be determined for each trading time interval for a plurality of trading algorithms. The plurality of trading algorithms may be set for each virtual asset. Each of the virtual assets may be set for each exchange. The plurality of trading algorithms are based on a first algorithm in which trades are concluded according to the standard deviation of the price fluctuation range determined based on the blinking indicator, a second algorithm in which trades are concluded based on a preset moving average, and the current It may include a third algorithm in which transactions are concluded according to the average value of change widths of candlesticks for the previous positive and negative candlesticks. The indicator reflecting the blink may be an indicator in which a deviation is calculated by adding possible price fluctuations, including a quantity canceled after a quote is submitted within a price fluctuation range, along with price fluctuations when a transaction occurs.

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

In the above equation, the Cap is the weight 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 may be a comprehensive evaluation score for the virtual asset, n may be the number of trading items, and TSVSi may be a comprehensive evaluation score for the ith trading item.

Here, the trade per day may be a value obtained by dividing the total number of trades by the trade period. Here, the Expect P&L may be determined based on the win rate within the trading period, the average rate of return per trade for profitable trades within the trading period, and the average rate of return per trade for trades that generate losses 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 obtained by reflecting a weight for a rebalancing criterion on a plurality of evaluation scores.

Additionally, for example, Expect P&L for the virtual asset may be determined by the following equation.

In the above equation, the Expect P&L is the expected profit/loss rate per transaction, and the Winr is the odds ratio for the transaction period. The WT ProfitAvg may be an average rate of return per transaction for profitable transactions within the trading period, and the LT ProfitAvg may be an average loss rate per transaction for transactions that generate losses within the trading period.

Additionally, for example, the portfolio management server determines after the time of receiving the first message through a prediction model using a neural network based on the plurality of evaluation scores determined through the data and evaluation model for the plurality of variables. A plurality of predictive evaluation scores may be determined. That is, the portfolio management server may determine a plurality of predicted evaluation scores after receiving the first message based on past evaluation scores and past data on a plurality of variables determining the past evaluation scores.

According to embodiments, the portfolio management server determines a plurality of evaluation scores through an evaluation model using a neural network based on data on a plurality of variables extracted from transaction information on trading items related to virtual assets, and determines the plurality of evaluation scores. By rebalancing the portfolio based on the evaluation score of , it is possible to rebalance the portfolio with the lowest risk versus profitability.

According to embodiments, the portfolio management server may determine an evaluation score reflecting characteristics of a virtual asset by using an index changed to a form suitable for evaluating an algorithm for a virtual asset when determining an evaluation score.

According to embodiments, the portfolio management server can accurately determine an evaluation score up to a current point in time through an evaluation model using multivariate LSTM and efficiently determine a predicted evaluation score after the current point in time through a predictive model using an autoencoder model. .

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

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
2 is a diagram showing the configuration of a program according to an embodiment.
3 illustrates a system for rebalancing a portfolio of virtual assets using a neural network according to an embodiment.
4 illustrates a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment.
5 is a flowchart of a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment.
6 is a table showing a plurality of variables for a plurality of trading items in a specific exchange according to an embodiment.
7 is a graph showing changes in virtual assets for trading items having an evaluation grade of A or higher according to an embodiment.
8 is a graph showing changes in virtual assets for trading items having an evaluation grade of less than A grade according to an embodiment.
9 is an example of an evaluation model and a prediction model according to an embodiment.
10 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 not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like 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, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

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

1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.

1 is a block diagram of an electronic device 101 within a network environment 100, according to various embodiments. Referring to FIG. 1 , in a network environment 100, an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or through a second network 199. It may communicate with at least one of the electronic device 104 or the server 108 through (eg, 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 an 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, 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 the antenna module 197 may be included. In some embodiments, in the electronic device 101, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added. In some embodiments, some of these components (eg, sensor module 176, camera module 180, or antenna module 197) are integrated into a single component (eg, 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 (eg, the program 140) to cause at least one other component (eg, hardware or software component) of the electronic device 101 connected to the processor 120. It can control and perform various data processing or calculations. According to one embodiment, as at least part of data processing or operation, the processor 120 transfers instructions or data received from other components (e.g., sensor module 176 or communication module 190) to volatile memory 132. , processing commands or data stored in the volatile memory 132 , and storing resultant data in the non-volatile memory 134 . According to one embodiment, the processor 120 may include a main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit ( NPU: neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, when the electronic device 101 includes the main processor 121 and the auxiliary processor 123, the auxiliary processor 123 may use less power than the main processor 121 or be set to be specialized for a designated function. can The secondary processor 123 may be implemented separately from or as part of the main processor 121 .

The secondary processor 123 may, for example, take the place of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or the main processor 121 is active (eg, running an application). ) state, together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to one embodiment, the auxiliary processor 123 (eg, image signal processor or communication processor) may be implemented as part of other functionally related components (eg, camera module 180 or communication module 190). there is. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model.

AI models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself where the artificial intelligence model is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning or reinforcement learning, but in the above example Not limited. The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the foregoing, but is not limited to the foregoing examples. The artificial intelligence model may include, in addition or alternatively, software structures in addition to hardware 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 . The data may include, for example, input data or output data for software (eg, program 140) and commands related thereto. The 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 an application 146 .

The input module 150 may receive a command or data to be used by a component (eg, the processor 120) of the electronic device 101 from the outside of the electronic device 101 (eg, a user). The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a 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. The speaker can be used for general purposes such as multimedia playback or recording playback. A receiver may be used to receive an incoming call. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 may 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 set to detect a touch or a pressure sensor set to measure the intensity of force generated by the touch.

The audio module 170 may convert sound into an electrical signal or vice versa. 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 connected directly or wirelessly to the electronic device 101 (eg: Sound may be output through the electronic device 102 (eg, a speaker or a headphone).

The sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, a 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 may include, 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 bio sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device 101 to 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 may 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 may convert electrical signals into mechanical stimuli (eg, vibration or motion) or electrical stimuli that a user may 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 may 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 may manage power supplied to the electronic device 101 . According to one embodiment, the power management module 188 may be implemented as at least part of a power management integrated circuit (PMIC), for example.

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 cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). Establishment and communication through the established communication channel may be supported. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, 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 (eg, : a local area network (LAN) communication module or a power line communication module). Among these communication modules, a corresponding communication module is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a telecommunications network such as a computer network (eg, a LAN or a WAN). These various types of communication modules may be integrated as one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips). The wireless communication module 192 uses subscriber information (eg, 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 may be identified or authenticated.

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

The antenna module 197 may transmit or receive signals or power to the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator formed 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 selected from the plurality of antennas by the communication module 190, for example. can be chosen A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module 197 in addition to the radiator.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module includes a printed circuit board, an RFIC disposed on or adjacent to a first surface (eg, a lower surface) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, array antennas) disposed on or adjacent to a second surface (eg, a top surface or a side surface) of the printed circuit board and capable of transmitting or receiving signals of 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 (eg, a 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 an 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 the same as or different from the electronic device 101 . According to an embodiment, all or part of operations executed in the electronic device 101 may be executed in one or more external electronic devices among 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 instead of executing the function or service by itself. Alternatively or additionally, one or more external electronic devices may be requested to perform the function or at least part of the service. One or more external electronic devices receiving the request may execute at least a part of the requested function or service or an additional function or service related to the request, and deliver the execution result to the electronic device 101 . The electronic device 101 may provide the result as at least part of a response to the request as it is or additionally processed. To this end, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may 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 (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide a service to the connected electronic device 101 . In addition, the server 108 may proceed with a membership sign-up procedure, store and manage various types of information of users subscribed as members, and provide various purchase and payment functions related to services. In addition, the server 108 may share execution data of service applications executed in each of the plurality of electronic devices 101 in real time so that the service can be shared among users. This server 108 may have the same configuration as a conventional web server or service server in terms of hardware. However, in terms of software, it may include a program module that is implemented through any language such as C, C++, Java, Python, Golang, or kotlin and performs 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 requests from clients or other servers to perform tasks and derives and provides work results. It means a computer system and the computer software (server program) installed for it. In addition, the server 108, in addition to the above-described server program, a series of application programs operating on the server 108 and various databases (DB: Database, hereinafter referred to as It should be understood as a broad concept including DB"). Accordingly, the server 108 classifies member registration information and various information and data about games, stores them in a DB, and manages them. This DB may be implemented inside or outside the server 108 . In addition, the server 108 may be implemented using server programs that are provided in various ways according to operating systems such as Windows, Linux, UNIX, and Macintosh on general server hardware, As a representative example, a web service can be implemented using IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, TOMCAT, etc. used in a Unix environment. In addition, the server 108 may interoperate with an authentication system and a payment system for user authentication of services or payment for purchases related to services.

The first network 198 and the second network 199 are a connection structure capable of exchanging information between nodes such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. means (Network). The first network 198 and the second network 199 include Internet, Local Area Network (LAN), Wireless Local Area Network (Wireless Local Area Network), Wide Area Network (WAN), Personal Area Network (PAN), and 3G , 4G, LTE, 5G, Wi-Fi, etc., but are not limited thereto. The first network 198 and the second network 199 may be closed first networks 198 and second networks 199 such as LAN and WAN, but are preferably open such as the Internet. The Internet includes protocols such as the TCP/IP protocol, TCP, and User Datagram Protocol (UDP), and various services that exist in the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) structure.

A database may have a general data structure implemented in a storage space (hard disk or memory) of a computer system using a database management program (DBMS). The database may have a data storage form in which data can be freely searched for (extracted), deleted, edited, added, and the like. Databases are relational database management systems (RDBMS) such as Oracle, Informix, 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 XML Native Databases such as Excelon, Tamino, and Sekaiju, and its functions may have appropriate fields or elements to achieve.

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

2 is a block diagram 200 illustrating a 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 in the operating system 142 for controlling one or more resources of the electronic device 101. can include The operating system 142 may include, for example, Android™, iOS™, Windows™, Symbian™, Tizen™, or Bada™. At least some of the programs 140 are, for example, preloaded in the electronic device 101 at the time of manufacture, or when used by a user, an external electronic device (eg, the electronic device 102 or 104), or a server ( 108)) can be downloaded or updated. All or part of program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or reclamation) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively include other hardware devices of electronic device 101 , such as input module 150 , sound output module 155 , display module 160 , 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 the function or information provided from one or more resources of the electronic device 101 may be used by the application 146 . The middleware 144 includes, for example, the application manager 201, the window manager 203, the multimedia manager 205, the resource manager 207, the power manager 209, the database manager 211, and the 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. can

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

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

Security manager 223 may provide system security or user authentication, for example. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101 . The voice recognition manager 227 transmits, for example, the user's voice data to the server 108, and at least partially based on the voice data, a command corresponding to a function to be performed in the electronic device 101; Alternatively, text data converted at least partially based 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 part 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, a home 251, a dialer 253, an SMS/MMS 255, an instant message (IM) 257, a browser 259, a camera 261, and an alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Albums (275), Watch (277), Health (279) (e.g. exercise or blood sugar) measurement of biometric information) or environmental information 281 (eg, measurement of atmospheric pressure, humidity, or temperature information). According to an embodiment, the application 146 may further include an information exchange application (not shown) capable of supporting 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 transmit designated information (eg, a call, message, or alarm) to an external electronic device, or a device management application configured to manage an external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a designated event (eg, mail reception) generated in another application (eg, the email application 269) of the electronic device 101 to an external electronic device. can Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide the notification information to the user of the electronic device 101 .

The device management application is, for example, a power source (eg, turn-on or turn-off) of an external electronic device that communicates with the electronic device 101 or some component thereof (eg, a display module or a camera module of the external electronic device). ) or functions (eg brightness, resolution, or focus). The device management application may additionally or alternatively support installation, deletion, or update of an application operating in an external electronic device.

Throughout this specification, a neural network, a neural network, and a network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may be generally referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network includes at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node 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, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may 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 in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having 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, virtual assets may be cryptocurrency. Cryptocurrency is a compound word of 'crypto-', which means 'encryption', and 'currency', which means currency and money. It is a digital asset that can prove In general, cryptocurrency can operate on a distributed ledger based on a blockchain or directed acyclic graph (DAG).

3 illustrates a system for rebalancing 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, a system 30 for rebalancing a portfolio of virtual assets includes a portfolio management server 310, a user terminal 320, an exchange server 330, a network 340, and a database ( 350) may be included.

The portfolio management server 310 receives a message requesting rebalancing for a portfolio of virtual assets from the user terminal 320 through the network 340, and rebalancing the portfolio related to the user terminal 320 ( 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 a user interface for rebalancing virtual assets to the user terminal 320 and transmit rebalancing information based on a user input for the corresponding user interface. The portfolio management server 310 receives transaction information on 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 on virtual assets. can do. Here, the transaction information on virtual assets may include information on off-chain transactions in which cryptocurrency is traded on an exchange, rather than information on on-chain transactions recorded in a distributed ledger of cryptocurrency. The portfolio management server 310 may determine rebalancing information of 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 of displaying a video screen and a user input interface. For example, the user terminal 320 may include a smart phone, a tablet PC, a PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a micro server, a global positioning system (GPS) device, an e-book reader, It may include digital broadcasting terminals, navigation devices, kiosks, MP3 players, digital cameras, home appliances, and other mobile or non-mobile computing devices. In addition, the user terminal 320 may include a wearable device such as a watch, glasses, hair band, and ring having 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 trading of virtual assets and manages transactions of virtual assets. For example, the exchange server 330 may transmit transaction information on 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 transfers 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 to. For example, exchange server 330 may include server 108 of FIG. 1 .

As shown in FIG. 3 , components of a system 30 that performs rebalancing on a portfolio of virtual assets may be connected through a network 340 . According to an embodiment, a network refers to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, LTE ( Long Term Evolution (5GPP) network, 5GPP (5rd 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 (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

Meanwhile, in the virtual asset market, a sell order and a buy order are formed by the selling price desired by the seller and the buyer, respectively, and the market price is formed as a result of mutual agreement. The more active the market is, the more buy and sell orders are placed at a price close to the agreed upon price, and the transaction is concluded at a price with a small difference from the market price. A transaction may be concluded at an out-of-price price. Using this point, there have been various attempts to make it appear as if actual market transactions are not being actively conducted, and these attempts have caused unexpected losses to service users. In particular, most of the abnormal attempts are made by abusing 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 quotes. . In response to this, the portfolio management server 310 according to the present disclosure measures the change in quotes submitted in the market, identifies and digitizes the normal range of price volatility that can occur based on the trading volume in the market, and digitizes the normal range of the price volatility. You can rebalance your portfolio based on .

In the case of quotes submitted in the cryptocurrency trading market, which are formed only through normal transactions, they show various patterns during the contracting process. Specifically, in the case of execution by market order, if the first quantity of the first quotation executed is greater than the trading volume, the quotation equal to the first quantity minus the trading volume remains. In the case of execution by limit order, if the first quantity is smaller than the trading volume and the limit price is not the price at which the second quotation will be executed, the quotation equal to the trading volume minus the 1st quantity remains as the opposite quotation, and the limit price is up to the quotation price equal to or greater than the second quotation. In the case of the price to be concluded, the number of bids equal to the difference between the second bid price and the second bid price remains. In other words, a single execution order causes the transaction volume to occur along with the quotation and change. If this is quantified, it is predicted how much the quotation and quotation submitted for the execution order corresponding to the average of the transaction volume will be executed and how much the quotation and price will change. It can be. Using this, the portfolio management server 310 according to the present disclosure may calculate an index through average calculation and deviation calculation with respect to the changeable range measured during a specific time interval in consideration of the transaction volume and the fluctuation range.

The portfolio management server 310 may generate an ideal indicator by determining a price change and calculating a deviation for each index constituent item when a transaction occurs according to all transactions. However, anomalous indicators are prone to error in the presence of unusual market disruptive behavior. In order to consider the quotation change for abnormal behavior, the portfolio management server 310 calculates the deviation by adding possible price fluctuations, including the quantity canceled after submitting the quotation within the price fluctuation range together with the price change when a transaction occurs, thereby calculating the deviation. (blink) A reflection indicator can be created. Alternatively, the portfolio management server 310 may generate a general index by measuring bid prices for each price fluctuation range multiple times and calculating a difference between the effective bid price and the current price within the price fluctuation range.

Since the generated indicators use a method of setting the baseline for the next interval based on the statistics of the previous interval, abnormal behaviors that deviate from the average value are reflected in the form of noise. That is, if a deviation for a volatility that is too large or too small is observed, the indicator is immediately reflected in the form of noise.

In addition, since the index is an index that derives a deviation of the measurement results of each section, more accurate results are derived as the number of samples increases. Therefore, the reliability of the index may increase in the case where a plurality of measured results are adopted in the case where a plurality of nodes form a network to generate and accumulate results respectively.

The portfolio management server 310 may extract index transaction data suitable 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. Hereinafter, a specific method for the portfolio management server 310 to perform rebalancing for a portfolio is exemplified.

4 illustrates 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 a first message requesting rebalancing from a user terminal.

For example, the first message may include at least one of first portfolio information on a virtual asset possessed by the user and authentication information on an exchange with which the user terminal has entered into a transaction. Here, the first portfolio information may include information on the trading item, the number of holdings, the date the transaction was concluded, and the exchange. 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.

In step S402 , the portfolio management server may acquire transaction information on trading items related to the first portfolio information for each exchange, based on receiving the first message.

For example, the portfolio management server may determine trading items based on the first portfolio information and obtain trading information for each exchange for the trading items. Here, the trading item related to the first portfolio information may be an item of a virtual asset traded by the user. That is, the portfolio management server may request transaction information for each exchange for the transaction items included in the first portfolio information and receive the transaction information from the exchange server. At this time, the portfolio management server may receive transaction information on trading items included in the first portfolio information from the exchange server after completing an authentication procedure with the exchange server based on the authentication information included in the first message.

In step S403, the portfolio management server may extract data on a plurality of variables for a trading period from the time the user holds the virtual asset to the time the first message is received based on the transaction information on the trading item. there is. For example, when a user has a plurality of virtual assets, the portfolio management server, based on transaction information on the trading item, for each of the plurality of virtual assets, from the time of holding the virtual asset to the time of receiving the first message Data on a plurality of variables can be extracted for the trading period of .

Here, the plurality of variables are, for the trading period, the total rate of return, the average rate of return per transaction for profitable transactions, the average rate of return per transaction for losses, and the standard deviation of the rate of return for profitable transactions. , the standard deviation of the loss rate for losing trades, the total number of trades, and the win rate.

For example, the total rate of return may be the value of the current virtual asset, that is, the value obtained by subtracting the value of the initial virtual asset (the investment principal amount) from the appraised amount divided by the principal amount of the initial self-investment value. The win rate may be a probability of generating a profit in one transaction. For example, the odds ratio may be a value obtained by dividing the total number of transactions by the number of profitable transactions. An average rate of return per trade for profitable trades may be determined based on a win rate and an average rate of return per trade. An average rate of return per transaction for a transaction in which a loss occurs may be determined based on a value obtained by subtracting a win rate from 1 and an average rate of loss per transaction.

In step S404, the portfolio management server may determine a plurality of evaluation scores through an evaluation model using a neural network based on the data on the plurality of variables.

Here, the evaluation score is a first value obtained by applying a first weight to the standard deviation of returns for transactions in which profits occurred within the period and a second value obtained by applying a second weight to the standard deviation of loss rates for transactions in which losses occurred within the period. It may be a value obtained by dividing the sum of the above by the average annual rate of return for the period. In this case, the first weight may be a value smaller 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 composed of data on a plurality of variables and a plurality of evaluation scores of correct answers 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 The input is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value by using a loss function that compares the output vector with the correct answer vector for each learning data. It can be learned in a direction in which the loss value becomes smaller.

For example, a plurality of evaluation scores may be determined for each trading time interval, trading algorithm, trading item, and exchange.

The plurality of evaluation scores may be determined for each trading time interval for a plurality of trading algorithms. Here, the plurality of trading algorithms include a first algorithm in which transactions are concluded according to the standard deviation for the price fluctuation range determined based on the blinking indicator, a second algorithm in which transactions are concluded based on a preset moving average, and the current As a reference, a third algorithm may be included in which a transaction is concluded according to the average value of change widths of candlesticks for previous positive and negative candlesticks. Here, the Blink reflection indicator may be an indicator in which a deviation is calculated by adding possible price fluctuations, including the quantity canceled after a quote is submitted within the price fluctuation range, together with the price fluctuation when a transaction occurs. For example, the transaction algorithm may be a method of automatically concluding a transaction when a specific condition is satisfied, and may have a different transaction algorithm according to the specific condition. Here, the transaction time interval may include 15 minutes, 1 hour, 4 hours, and 24 hours. That is, the plurality of transaction algorithms may determine whether a specific condition for concluding a transaction is satisfied for each set transaction time interval. The transaction time interval is not limited to the present disclosure, and a larger number of transaction time intervals may be set. Through this, the portfolio management server may determine an evaluation score for the case of performing transactions at respective trading time intervals for different trading algorithms based on data on a plurality of variables.

The plurality of trading algorithms may 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. An evaluation score may be determined for each distance time interval for a plurality of transaction algorithms.

Each of the virtual assets may be set for each exchange. For example, evaluation scores may be determined for Bitcoin and Ethereum for other exchanges other than the exchange where the user has entered into a transaction. That is, the evaluation scores of Exchange A for Bitcoin and Ethereum may be determined for each distance time interval for a plurality of trading algorithms, and the evaluation scores for Exchange B for Bitcoin and Ethereum may be determined for a plurality of trading algorithms. It may be determined for each distance time interval.

In step S405, the portfolio management server may determine rebalancing information for the first portfolio based on the plurality of evaluation scores.

Here, the rebalancing information for the first portfolio may include weights for virtual assets. For example, when the virtual assets held by the user are Bitcoin and Ethereum, the rebalancing information for the first portfolio may include a weight to Bitcoin and a weight to Ethereum.

For example, the weight 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 a value obtained by dividing the total number of transactions by the transaction period. The expected profit/loss rate per transaction may be determined based on the win rate within the trading period, the average rate of return per transaction for profitable transactions within the trading period, and the average loss rate per transaction for transactions with losses within the trading period. there is.

For example, the share of the most assets may be determined by Equation 1 below.

In Equation 1, the Cap is the weight 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 of the virtual asset; The TSVS may be a comprehensive evaluation score for the virtual asset, n may be the number of trading items, and the TSVSi may be a comprehensive evaluation score for the i-th trading item.

Here, the trade per day may be a value obtained by dividing the total number of trades by the trade period. Here, the Expect P&L may be determined based on the win rate within the trading period, the average rate of return per trade for profitable trades within the trading period, and the average rate of return per trade for trades that generate losses 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 obtained by reflecting a weight for a rebalancing criterion on a plurality of evaluation scores.

Through this, the portfolio management server may perform rebalancing of the portfolio according to the characteristics of the virtual asset by considering various factors such as a trading algorithm, a trading time interval, and an exchange related to the virtual asset.

For example, Expect P&L for the virtual asset may be determined by Equation 2 below.

In Equation 2, the Expect P&L is the expected profit/loss rate per transaction, and the Winr is the odds ratio for the transaction period. The WT ProfitAvg may be an average rate of return per transaction for profitable transactions within the trading period, and the LT ProfitAvg may be an average loss rate per transaction for transactions that generate losses within the trading period.

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

For example, the evaluation score may be determined by Equation 3 below.

The StrategyValueScore is the evaluation score, the Total Profit is the total rate of return, the TradingDay is the trading period, the Profit sd (+) is the standard deviation of rates of return for transactions in which profits occurred within the period, and the Profit sd ( -) may be the standard deviation of the loss rate for transactions in which a loss occurred within the period.

In step S406, the portfolio management server may transmit a second message including rebalancing information for the first portfolio to the user terminal.

In step S407, the portfolio management server may perform rebalancing on the first portfolio based on the rebalancing information based on receiving a rebalancing approval message from the user terminal.

Additionally, for example, when only one virtual asset is included in the portfolio, the first message requesting rebalancing may further include a value for a rebalancing criterion selected by the user. When the value of the rebalancing criterion corresponds to the trading algorithm, the portfolio management server may determine evaluation scores for each trading time interval for a plurality of trading algorithms for the one most asset. The portfolio management server may set evaluation scores for each trading time interval for the plurality of trading algorithms for each exchange. Through this, the portfolio management server may determine a weight for each of a plurality of trading algorithms. In addition, when the value for the rebalancing criterion corresponds to the trading time interval, the portfolio management server may set evaluation scores for each trading algorithm for the plurality of trading time intervals for each exchange, and the portfolio management server may set the trading time interval for the trading time interval. weight can be determined. In addition, for example, if the value for the rebalancing criterion corresponds to the exchange, the portfolio management server may set the evaluation score for each trading algorithm for the plurality of exchanges for each trading time interval, and the portfolio management server may set the exchange as a standard. You can determine your weighting on the exchange.

5 is a flowchart of a method of performing rebalancing on a portfolio of virtual assets using a neural network according to an embodiment. 6 is a table showing a plurality of variables for a plurality of trading items in a specific exchange according to an embodiment. 7 is a graph showing changes in virtual assets for trading items having an evaluation grade of A or higher according to an embodiment. 8 is a graph showing changes in virtual assets for trading items having an evaluation grade of less than A grade according to an embodiment. The embodiments of FIGS. 5 to 8 may be combined with various embodiments of the present disclosure.

Referring to FIG. 5 , in step S501, the portfolio management server may receive a first message requesting rebalancing from a user terminal. For example, the first message may include at least one of first portfolio information on a virtual asset possessed by the user and authentication information on an exchange with which the user terminal has entered into a transaction.

In step S502, the portfolio management server may determine whether authentication information exists in the first message. For example, authentication information may include at least one of an ID related to a user terminal, an authentication number, or biometric information for authentication. Here, the biometric information is biometric information capable of identifying the user, and may include at least one of information about the user's fingerprint, information about the user's iris, and information about the user's face.

In step S503, based on receiving the authentication information in the first message, the portfolio management server may receive transaction information on a trading item related to the first portfolio information from the exchange server. Here, the trading item related to the first portfolio information may be an item of a virtual asset traded by the user.

For example, the portfolio management server may receive transaction information on trading items included in the first portfolio information from the exchange server after completing an authentication procedure with the exchange server based on authentication information included in the first message. there is.

In step S504, based on the failure to receive authentication information in the first message, the portfolio management server may obtain transaction information on a trading item related to the first portfolio information through web crawling of a plurality of exchange servers. .

Referring to FIG. 6, the portfolio management server draws data on a plurality of variables for a trading period from the time the user holds the virtual asset to the time the first message is received based on the transaction information for the trading item. It can be extracted as shown in Table 6.

In the table of FIG. 6, English letters such as BTC and ETH represent the items of virtual assets, and the portfolio management server calculates the total return within the trading period and total transactions within the trading period for each item of the most valuable asset based on the transaction information. The number of times, the win rate within the trading period, the standard deviation of the rate of return for profitable transactions within the trading period, and the standard deviation of the loss rate for trading with losses within the trading period may be extracted. For example, in the case of BTC, the total return within the trading period is 1534.78%, the total number of trades is 296, the odds ratio is 26.01%, the return on trades that have been profitable in relation to the standard deviation is 15.95%, and the standard deviation and The loss ratio for trades with losses associated with them may be 1.31%.

In step S505, the portfolio management server may determine a plurality of evaluation scores through an evaluation model using a neural network based on data on a plurality of variables. In step S506, the portfolio management server may determine whether the number of trading items included in the first portfolio is plural.

Referring to FIG. 6 , for example, in the case of analyzing evaluation scores for each trading item, the portfolio management server may determine an evaluation score for each trading item in the exchange based on data on a plurality of variables. For example, the evaluation score of BTC can be determined as 76.23 points by Equation 3 above.

In step S507, when the number of trading items included in the first portfolio is plural, the portfolio management server may determine rebalancing information for the first portfolio based on the comprehensive evaluation score.

For example, the portfolio management server may determine the proportion of virtual assets included in the first portfolio by Equation 1 described above.

Here, the comprehensive evaluation score is a weight obtained by applying a first reference weight for a trading time interval, a second reference weight for a trading algorithm, a third reference weight for an exchange, and a fourth reference weight for a trading item to a plurality of evaluation scores. may be an average value. The reference weight may be a weight applied to evaluation scores determined for each corresponding rebalancing criterion. For example, when a first criterion weight for each trading time interval is applied, when determining an evaluation score for Bitcoin among trading items included in the first portfolio, a first criterion weight for the evaluation score determined for each trading time interval. may be applied. 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 may perform rebalancing of the portfolio by reflecting the investment direction desired by the user.

In step S508, when there is only one transaction item included in the first portfolio, the portfolio management server may determine rebalancing information for the first portfolio based on a value for a rebalancing criterion.

For example, a value for a rebalancing criterion may be included in the first message. At this time, the portfolio management server replaces the overall evaluation score with the evaluation score for the rebalancing criterion in Equation 1 based on the value for the rebalancing criterion, replaces the number of trading items with the number related to the rebalancing criterion, , the overall evaluation score for the ith transaction item can be replaced with the evaluation score for the ith rebalancing criterion. That is, for example, when the value for the rebalancing criterion corresponds to the trading algorithm, the portfolio management server uses Equation 1 described above, but converts the overall evaluation score to the evaluation score for the trading algorithm currently set by the user terminal. By substituting the number of trading items with the number of trading algorithms, and replacing the overall evaluation score for the i-th trading item with the evaluation score for the i-th trading algorithm, the weighting of the trading algorithm can be determined.

In step S509, the portfolio management server may determine whether an evaluation grade equal to or greater than B exists.

Referring to FIG. 6 , the portfolio management server may determine an evaluation level based on the evaluation score. For example, the portfolio management server may determine an evaluation grade according to a range included in the evaluation score. The range may be preset in the portfolio management server. In this case, when the evaluation score is 60 points or more, it may be determined as A+ grade, and when the evaluation score is between 50 points and 60 points, it may be determined as grade A. When the evaluation score is between 40 and 50 points, it may be determined as a B+ grade, and when the evaluation score is between 35 and 40 points, it may be determined as a B grade. If the evaluation score is between 30 and 35 points, it may be determined as a C+ grade, and if the evaluation score is 30 points or less, it may be determined as a C grade.

For example, in the case of analyzing the evaluation score for each trading item, the asset change graph for BTC (610) with an evaluation score of 76.23 points and an A+ grade (710) and ETH (610) with an A+ grade with an evaluation score of 93.60 points An asset change graph 710 for may appear as shown in FIG. 7 . In addition, an asset change graph 720 for an ADA 620 having an A grade of 58.36 points and an asset change graph 720 for an ETC 620 having an evaluation score of 57.37 points may be displayed as shown in FIG. 7 . For example, the asset change graph 810 for WAXP (630) with an evaluation score of 43.47 points and a B+ grade and the asset change graph 810 for ZIL (640) with an evaluation score of 38.94 points and a B grade are shown in FIG. may appear as In addition, an asset change graph 820 for MED (660) with an evaluation score of 27.07 and a C grade and an asset change graph 820 for an OMG (650) with an evaluation score of 28.81 and a C grade will appear as shown in FIG. can

In step S510, if there is no evaluation grade equal to or greater than B, the portfolio management server may determine a plurality of predicted evaluation scores after receiving the first message through a prediction model using a neural network.

Additionally, for example, the portfolio management server determines after the time of receiving the first message through a prediction model using a neural network based on the plurality of evaluation scores determined through the data and evaluation model for the plurality of variables. A plurality of predictive evaluation scores may be determined. That is, the portfolio management server may determine a plurality of predicted evaluation scores after receiving the first message based on past evaluation scores and past data on a plurality of variables determining the past evaluation scores.

In step S511, the portfolio management server may transmit a second message including rebalancing information for the first portfolio to the user terminal.

For example, if there is an evaluation grade equal to or greater than B, the portfolio management server may transmit a second message including rebalancing information for the first portfolio to the user terminal.

For example, if there is no evaluation grade equal to or greater than B, the portfolio management server includes rebalancing information for the first portfolio and predictive rebalancing information for the first portfolio determined based on the plurality of predicted evaluation scores. 2 The message can be transmitted to the user terminal.

In step S512, the portfolio management server may determine whether to receive a rebalancing approval message from the user terminal.

In step S513, when the approval message for rebalancing is not received from the user terminal, the portfolio management server may receive a change message for rebalancing from the user terminal. For example, the change message for rebalancing may include information about the proportion of virtual assets changed by the user.

In step S514, the portfolio management server may perform rebalancing.

For example, when receiving an approval message for rebalancing from the user terminal, the portfolio management server may perform rebalancing on the first portfolio based on the rebalancing information.

For example, when a change message for rebalancing is received from the user terminal, the portfolio management server performs rebalancing on the first portfolio based on the rebalancing information and information on the ratio of virtual assets changed by the user. can

9 is an example of an evaluation model and a prediction model according to an embodiment. The embodiment of FIG. 9 can be combined with various embodiments of the present disclosure.

Referring to FIG. 9 , the neural network used for the evaluation model may be a multivariate long short term memory networks (LSTM) model. In general, a recurrent neural network (RNN) can effectively model time-series information because hidden layer values for an existing input stored therein are considered in an output for a next input value. However, since RNN is a structure that depends on past observation values, problems such as vanishing gradient or exploding gradient may occur. A model to solve this problem is LSTM, and by replacing nodes inside the LSTM with memory cells, information can be accumulated or some of past information can be deleted, and the problem of the RNN can be supplemented.

For example, a neural network may include an input layer 910 , one or more hidden layers 920 , and an output layer 930 .

For example, the one or more hidden layers 920 include one or more LSTM blocks, and one LSTM block includes a memory cell, an input gate, an erase 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 performs a recursive operation of using a value output from a memory cell at a previous point in time as its own input. can For example, when the current time point is t, a value output by a memory cell at the current time point t may be influenced by values of memory cells in the past. The memory cell may output a cell state (C _t ) value and a hidden state (h _t ) value. That is, the memory cell uses the cell state value (C _t-1 ) and the 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. can be used as

For example, the input gate 922, the deletion gate 921, and the output gate 923 all include a sigmoid layer, and it may indicate how much information input through the sigmoid layer is transmitted. For example, a sigmoid layer is a sigmoid function ( ) may be a layer whose activation function is Also, for example, the cell state 924 is controlled through the input gate 922, the deletion gate 921, and the output gate 923, and weights according to each gate and input may exist.

For example, data for a plurality of variables may be vectorized through data preprocessing. That is, data for a plurality of variables may be converted into a plurality of input vectors composed of an input vector for each trading 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 is generated based on the input vectors h _t-1 (hidden state at time t-1) and x _t (input value at time t) ), a value between 0 and 1 can be passed as C _t-1 . Here, a value between 0 and 1 is the amount of information that has gone through the deletion process. The closer to 0, the more information is deleted, and the closer to 1, the more intact information can be transmitted.

For example, the input gate 922 may determine a value to be updated through a sigmoid layer, and a tanh layer may generate a C _t vector, which is new candidate values, and store it in the cell state 924 . tanh means a nonlinear activation function (hyperbolic tangent function).

For example, a new cell state C _t may be created by updating the previous cell state C _t-1 . That is, information about the cell state 924 is deleted by multiplying f _t by the cell state, and a value obtained by scaling the updated value may be added.

For example, the output gate 923 may determine a portion of a cell state to be output based on a plurality of input vectors in the sigmoid layer, and the output gate 923 converts the cell state determined in the sigmoid layer to tanh Through the layer, a value between -1 and 1 can be multiplied with the output value.

For example, the evaluation model may be an LSTM model in which the deletion gate 921 and the input gate 922 are combined. In this case, since only the old information to which new information is added is deleted, the operation can be performed more quickly.

Therefore, 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) and determines each criterion. evaluation score can be determined.

Referring to FIG. 9 , the prediction model may be an auto encoder model. An autoencoder model is an unsupervised learning algorithm that has strengths in expressing linear and non-linear relationships between data, removing noise from data, and inferring patterns. An autoencoder neural network is a structure in which two neural network layers are combined in a symmetrical form. Data input through an input layer determines feature values through an encoding layer and restores feature values in a decoding layer, so that the answer data in the output layer can be learned as similarly as possible.

For example, an autoencoder neural network may be constructed based on a convolutional neural network and may include an input layer 940, two encoding layers 950, two decoding layers 960, and an output layer 970. can A Rectified Linear Unit (ReLU) function may be used as an activation function of the encoding layer and the decoding layer, and a linear function may be used as an activation function of the output layer. Here, the ReLU function is a function that returns a value of 0 for negative values and a corresponding value for positive values. At this time, the autoencoder neural network may symmetrically determine the weights of the encoder layer and the weights of the decoder layer. Through this, by reducing the learning amount for the autoencoder neural network by half, the learning speed can be improved and the risk of overfitting can be reduced.

For example, the portfolio management server may generate an input vector for an autoencoder neural network through preprocessing of data for a plurality of variables and data for a plurality of evaluation scores determined through an evaluation model, and the portfolio management server may generate the input vector for the autoencoder neural network. By passing the vector through the encoding layer to determine the feature value and restoring the feature value in the decoding layer, it is possible to determine a predicted evaluation score that is as similar as possible to the evaluation score of the correct answer in the output layer. That is, the portfolio management server may determine a plurality of predicted evaluation scores after receiving the first message based on past evaluation scores and past data on a plurality of variables determining the past evaluation scores.

10 is a block diagram showing the configuration of a portfolio management server according to an embodiment. One embodiment of FIG. 10 may be combined with various embodiments of the present disclosure.

As shown in FIG. 10 , the portfolio management server 1000 may include a processor 1010 , a communication unit 1020 and a memory 1030 . However, not all components shown in FIG. 10 are essential components of the portfolio management server 1000 . The portfolio management server 1000 may be implemented by more components than those shown in FIG. 10, or the portfolio management server 1000 may be implemented by fewer components than those shown in FIG. For example, the portfolio management server 1000 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 1010, the communication unit 1020, and the memory 1030. may be

The processor 1010 typically controls the overall operation of the portfolio management server 1000 . The processor 1010 may include one or more processors to control other elements included in the portfolio management server 1000 . For example, the processor 1010 may generally control the communication unit 1020 and the memory 1030 by executing programs stored in the memory 1030 . In addition, the processor 1010 may perform the functions of the portfolio management server 1000 described in FIGS. 3 to 9 by executing programs stored in the memory 1030 .

The communication unit 1020 may include one or more components that allow the portfolio management server 1000 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 1000 or a sensing device, but is not limited thereto. The communication unit 1020 may receive a user input from another electronic device or data stored in an external device from an external device through a network.

For example, the communication unit 1020 may transmit/receive a message for establishing a connection with at least one device. The communication unit 1020 may transmit information generated by the processor 1010 to at least one device connected to the server. The communication unit 1020 may receive information from at least one device connected to the server. The communication unit 1020 may transmit information related to the received information in response to information received from at least one device.

The memory 1030 may store programs for processing and control of the processor 1010 . For example, the memory 1030 may store information input to a server or information received from another device through a network. Also, the memory 1030 may store data generated by the processor 1010 . The memory 1030 may store information input to or output from the portfolio management server 1000 .

The memory 1030 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), 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 , an optical disk, and at least one type of storage medium.

The embodiments described above may be implemented as 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, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable 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. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in 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 hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. 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.

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

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

delete

delete

Claims (12)

A method for a portfolio management server to rebalance a portfolio of virtual assets using a neural network, the method comprising:
Receiving a first message requesting rebalancing from a user terminal;
The first message includes first portfolio information on virtual assets owned by the user,
Based on receiving the first message, acquiring transaction information for each trading item related to the first portfolio information;
extracting data on a plurality of variables for a trading period from the time the user holds the virtual asset to the time the first message is received based on the transaction information for the trading item;
The plurality of variables are, for the trading period, the total rate of return, the average rate of return per transaction for profitable transactions, the average rate of return per transaction for losses, the standard deviation of the rate of return for profitable transactions, Include the standard deviation of the loss rate for losing trades, the total number of trades, and the win rate;
determining a plurality of evaluation scores through an evaluation model using a neural network based on the data on the plurality of variables;
determining rebalancing information for the first portfolio based on the plurality of evaluation scores;
Transmitting a second message including rebalancing information for the first portfolio to the user terminal; and
Based on receiving an approval message for rebalancing from the user terminal, performing rebalancing on the first portfolio based on the rebalancing information; Including,
The rebalancing information for the first portfolio includes a weight for virtual assets,
The weight 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 value obtained by dividing the total number of transactions by the transaction period,
The expected profit/loss rate per transaction is determined based on the win rate within the trading period, the average rate of return per transaction for profitable transactions within the trading period, and the average loss rate per transaction for losses occurring within the trading period, ,
Each of the plurality of evaluation scores is determined by the following equation for each trading time interval, trading algorithm, and exchange,
The plurality of evaluation scores are determined for each trading time interval for a plurality of trading algorithms,
The plurality of trading algorithms are set for each virtual asset,
Each virtual asset is set for each exchange,
The plurality of trading algorithms are based on a first algorithm in which trades are concluded according to the standard deviation of the price fluctuation range determined based on the blinking indicator, a second algorithm in which trades are concluded based on a preset moving average, and the current Including a third algorithm in which transactions are concluded according to the average value of change widths of candles for previous positive and negative candlesticks,
The Blink reflection indicator is an indicator calculated by adding possible price fluctuations, including the quantity canceled after a quote is submitted within the price fluctuation range, along with the price fluctuation when a transaction occurs, and the deviation is calculated.

In the above equation, the StrategyValueScore is the evaluation score, the Total Profit is the total rate of return, the TradingDay is the trading period, the Profit sd (+) is the standard deviation of the rate of return for transactions generating profits within the trading period, , The Profit sd (-) is the standard deviation of the loss rate for transactions in which losses occurred during the trading period,
method.
delete delete According to claim 1,
The neural network includes an input layer, one or more hidden layers and an output layer;
Each learning data composed of data on a plurality of variables and a plurality of evaluation scores of correct answers 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 The input is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value by using a loss function that compares the output vector with the correct answer vector for each learning data. Learning in the direction in which the loss value becomes smaller,
method.
delete In the portfolio management server including at least one processor, at least one memory and a communication unit,
The at least one processor is:
Receiving a first message requesting rebalancing from a user terminal;
The first message includes first portfolio information on virtual assets owned by the user,
Based on receiving the first message, acquiring transaction information for each trading item related to the first portfolio information,
Extracting data for a plurality of variables for a trading period from the time the user holds the virtual asset to the time the first message is received based on the transaction information for the trading item;
The plurality of variables are, for the trading period, the total rate of return, the average rate of return per transaction for profitable transactions, the average rate of return per transaction for losses, the standard deviation of the rate of return for profitable transactions, Include the standard deviation of the loss rate for losing trades, the total number of trades, and the win rate;
Based on the data on the plurality of variables, a plurality of evaluation scores are determined through an evaluation model using a neural network,
Determining rebalancing information for the first portfolio based on the plurality of evaluation scores;
Transmitting a second message including rebalancing information for the first portfolio to the user terminal;
Based on receiving an approval message for rebalancing from the user terminal, rebalancing is performed on the first portfolio based on the rebalancing information;
The rebalancing information for the first portfolio includes a weight for virtual assets,
The weight 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 value obtained by dividing the total number of transactions by the transaction period,
The expected profit/loss rate per transaction is determined based on the win rate within the trading period, the average rate of return per transaction for profitable transactions within the trading period, and the average loss rate per transaction for losses occurring within the trading period, ,
The plurality of evaluation scores are determined for each trading time interval for each of the plurality of trading algorithms,
The plurality of trading algorithms are set for each virtual asset,
Each of the virtual assets is set for each exchange,
The plurality of trading algorithms are based on a first algorithm in which trades are concluded according to the standard deviation of the price fluctuation range determined based on the blinking indicator, a second algorithm in which trades are concluded based on a preset moving average, and the current Including a third algorithm in which transactions are concluded according to the average value of the change width of the candlestick for the previous positive and negative candlesticks,
The Blink reflection indicator is an indicator calculated by adding possible price fluctuations, including the quantity canceled after a quote is submitted within the price fluctuation range, along with the price fluctuation when a transaction occurs, and the deviation is calculated.
Each of the plurality of evaluation scores is determined by the following equation for each trading time interval, trading algorithm, and exchange,

In the above formula, the StrategyValueScore is an evaluation score, the Total Profit is the total rate of return, the TradingDay is the trading period, the Profit sd (+) is the standard deviation of the rates of return for transactions in which profits occurred within the trading period, The Profit sd (-) is the standard deviation of the loss rate for transactions in which losses occurred within the trading period,
Portfolio Management Server.
delete delete According to claim 6,
The neural network includes an input layer, one or more hidden layers and an output layer;
Each learning data composed of data on a plurality of variables and a plurality of evaluation scores of correct answers 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 The input is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value by using a loss function that compares the output vector with the correct answer vector for each learning data. Learning in the direction in which the loss value becomes smaller,
Portfolio Management Server.
delete A computer program stored in a computer readable recording medium in order to execute the method of claim 1 in combination with hardware.
A computer readable recording medium storing a computer program combined with hardware to execute the method of claim 1.

Images