KR20230166412A - Method of recommending stock items using announcement data and system thereof - Google Patents

Abstract

The present invention relates to a method and system for recommending stock items using public data. The method for recommending stock items according to the present invention includes the steps of classifying stocks listed on the market into value stocks and growth stocks, and exposing value investments by institutions that provide public data. Calculating the degree, calculating the value investment attractiveness by stock item using the calculation results of value investment exposure by institution and public data, intermediately selecting stock items that satisfy the preset upper standards as a result of calculating the attractiveness of value investment by stock item. It may include a step of final selection of stock items that are in a declining state during a preset period among the intermediately selected stock items.

Description

Stock recommendation method and system using public data {METHOD OF RECOMMENDING STOCK ITEMS USING ANNOUNCEMENT DATA AND SYSTEM THEREOF}

The present invention relates to a method and system for recommending stock items to purchase based on publicly disclosed data.

With the development of information and communication technology, stock and product investments are actively being made online, and accordingly, the number of individual investors is increasing significantly.

As the number of individual investors increases and trading becomes more active, the number of individual investors who are interested in overseas stocks is also increasing as they feel the need to trade not only domestic stocks but also foreign stocks.

These general individual investors have a strong tendency to invest in stocks without being based on sophisticated analysis when selecting investment items and have a strong tendency to pursue maximization of profits. Accordingly, individual investors tend to suffer large losses rather than maximize securities profits.

In particular, individual investors are very interested in overseas stocks, but it is difficult to analyze foreign stock items due to reasons such as collection of related data and language, and exchange rate fluctuations must be taken into account, so individual investors tend to be reluctant to invest in overseas stocks. there is.

The technology behind the invention has been written to facilitate easier understanding of the invention. It should not be understood as an admission that matters described in the technology underlying the invention exist as prior art.

Accordingly, the inventors of the present invention sought to study a stock item recommendation method that would allow individual investors to easily invest in overseas stocks.

As a result, the inventors of the present invention developed a method and system for recommending stock items with high investment return and accuracy using public information on the status of stock items held by large institutions.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the above-mentioned problems, the stock item recommendation method according to an embodiment of the present invention includes the steps of dividing stocks listed on the market into value stocks and growth stocks, calculating the value investment exposure for each institution providing public disclosure data, A step of calculating the value investment attractiveness of each stock item using the calculation results of value investment exposure by institution and public data, a step of intermediate selection of stock items that satisfy the upper standard set in advance as a result of the calculation of value investment attractiveness of each stock item, and an intermediate selection step. It may include a final selection of stock items that are in a declining state during a preset period among stock items.

According to another feature of the present invention, the step of classifying value stocks and growth stocks can be done by scoring stocks listed on the market with a number between 0 and 100.

According to another feature of the present invention, the method of scoring stocks listed on the market is a method of using the Value Score and Growth Score published by investment information companies, and various types of financial statements. A method of calculating percentages according to each direction of the indicators and then using the average of the calculated percentages of each indicator, a method of applying supervised learning of machine learning to various indicators of financial statements, and machine learning Through unsupervised learning, stocks are divided into two groups and the representative stocks of each group are identified. One group is value stocks and the other group is growth stocks. The closer to the center coordinate of each group, the higher the corresponding characteristic is considered. Any one of the methods can be used.

According to another feature of the present invention, the method of using supervised learning of machine learning includes the steps of selecting stocks judged to be value stocks and stocks judged to be growth stocks by experts, and then setting them as labeled data; It may include learning a classification algorithm based on labeled data.

According to another feature of the present invention, the step of calculating the value investment exposure for each institution providing public data determines whether the investment style of the institutions providing public data is a value stock investment style or a growth stock investment style based on stock records held in the past. can be calculated.

According to another feature of the present invention, the step of calculating the value investment exposure for each institution providing public data is a weighted average in proportion to the trading volume of each record for each record held in the past by the institution providing public data, or regardless of trading volume. It can be calculated using either a simple average method or a method where the weight is varied over time and more weight is given to recently held stocks.

According to another feature of the present invention, the step of calculating the value investment attractiveness for each stock item is selecting the scope of the institution to determine whether to calculate the value investment attractiveness based on the published data of the institutions providing the disclosed data. Stage, scope of institutions The institutions selected in the selection stage select newly purchased stock items and stock items with an increased proportion than the existing holdings from the last quarter's public disclosure data. Stock items selected in the target stock selection stage and target stock selection stage. It may include a value investment attractiveness calculation step for calculating the value investment attractiveness.

According to another feature of the present invention, in the value investment attractiveness calculation step, for each of the stock items selected in the target stock selection step, the value investment exposure scores of institutions that purchased the selected stock items are summed and divided into the total number of institutions. The first method of division is to add up the value investment exposure scores of institutions that purchased the selected stock items for each of the stock items selected in the target stock selection stage, divide by the total number of institutions, and then each institution newly The second method gives additional weight to the amount purchased or the amount that increases the holding of the stock item in consideration of its proportion in the institution's operating scale, stocks selected for each of the stock items selected in the target stock selection stage. A third method is to add the value investment exposure scores of the institutions that purchased the stocks, divide them by the total number of institutions, and then give additional weight considering each institution's expertise and skill level in the sector to which the stock belongs, and select target stocks. For each of the stock items selected in the step, the value investment exposure scores of the institutions that purchased the selected stock items are summed, divided by the total number of institutions, and then the amount or number of new purchases of the stock item by each institution is calculated. The amount of increased holdings can be calculated using any one of the fourth methods, which gives additional weight considering the proportion of the institution's operating scale and each institution's expertise and skill level in the sector to which the stock belongs. You can.

According to another feature of the present invention, the preset period in the final selection of stock items can be set by estimating as close as possible the time when the institution purchased the finally selected stock items, taking into account the timing of public data announcement.

The stock item recommendation system according to an embodiment of the present invention selects recommended stock items using public data announced quarterly on stock items held by institutions with assets of $100 million or more, and sends the selected recommended stock items to the outside. A stock item recommendation server and a stock item recommendation platform that provide a stock item recommendation platform are installed, and may include a plurality of user devices that receive recommended stock items from the stock item recommendation server through the stock item recommendation platform.

According to another feature of the present invention, the stock item recommendation server includes a communication interface for receiving public data and transmitting recommended stock items to the outside, and a memory for storing a program or algorithm for selecting public data announced by institutions and recommended stock items. , and operates in connection with memory, classifies stocks listed on the market into value stocks and growth stocks, calculates the value investment exposure for each institution that provides disclosure data, and then uses the value investment exposure calculation results and disclosure data for each institution. The value investment attractiveness of each stock item is calculated, and as a result of the value investment attractiveness calculation for each stock item, stock items that satisfy the preset upper standards are selected, and among the selected stock items, the stock items that have declined during the preset period are finally selected. You can select and include recommended processors.

According to another feature of the present invention, the processor uses value stock scores and growth stock scores announced by investment information companies, calculates percentages for various indicators of financial statements according to each direction, and then averages the percentages of each calculated indicator. Through a method of using one value, a method of applying supervised learning of machine learning to various indicators of financial statements, and unsupervised learning of machine learning, stocks are divided into two groups and representative stocks of each group are identified, and one group is value stocks. , Another group is growth stocks, and then the stocks listed on the market are scored using one of the following methods, where the closer to the center coordinate of each group is considered to have higher corresponding characteristics, the stocks are divided into value stocks and growth stocks. can be distinguished.

According to another feature of the present invention, the processor calculates a weighted average or simple average in proportion to the transaction volume of each record for each record held in the past by an institution providing public disclosure data, and varies the weight according to the passage of time to provide the latest You can calculate whether an institution has a value stock investment style or a growth stock investment style by using one of the calculation methods that gives more weight to the stocks held by .

According to another feature of the present invention, the processor selects whether to calculate the attractiveness of value investment based on the disclosed data of any of the institutions providing the disclosed data, and the selected institutions make new purchases from the disclosed data in the last quarter. After selecting one stock item and stock items with an increased proportion than the existing holdings, the attractiveness of value investment can be calculated for the selected stock items.

According to another feature of the present invention, the processor adds up the value investment exposure scores of institutions that purchased the selected stock items for each of the selected stock items and divides them by the total number of institutions, or each institution corresponds to the divided value. The amount of newly purchased stock items or the amount of increased holdings of the stock items is weighted in consideration of their proportion in the institution's operating scale, or by considering each institution's expertise and skill level in the sector to which the stock belongs. By giving weights, you can calculate the attractiveness of value investment.

Specific details of other embodiments are included in the detailed description and drawings.

The present invention can provide a stock item recommendation method and system that allows individual investors to secure a greater safety margin and purchase overseas stocks at a good price.

In addition, the present invention can provide a stock item recommendation method and system with improved reliability by recommending stock items using public information related to the status of stock items held by large overseas institutions.

The effects according to the present invention are not limited to the details exemplified above, and further various effects are included within the present invention.

1 is a schematic diagram of a stock item recommendation system according to an embodiment of the present invention.
Figure 2 is a block diagram showing the configuration of a user device according to an embodiment of the present invention.
Figure 3 is a block diagram showing the configuration of a stock item recommendation server according to an embodiment of the present invention.
Figure 4 is a flowchart sequentially showing a stock item recommendation method according to an embodiment of the present invention.
Figure 5 is a flowchart showing the process of calculating investment attractiveness for each stock item according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms, but the present embodiments only serve to ensure that the disclosure of the present invention is complete and are within the scope of common knowledge in the technical field to which the present invention pertains. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, similar reference numbers may be used for similar components.

In this document, expressions such as “have,” “may have,” “includes,” or “may include” refer to the existence of the corresponding feature (e.g., a numerical value, function, operation, or component such as a part). , and does not rule out the existence of additional features.

In this document, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” includes (1) at least one A, (2) at least one B, Or (3) it may refer to all cases including both at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in this document can modify various components regardless of order and/or importance, and can refer to one component. It is only used to distinguish from other components and does not limit the components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, the first component may be renamed as the second component without departing from the scope of rights described in this document, and similarly, the second component may also be renamed as the first component.

A component (e.g., a first component) is “(operatively or communicatively) coupled with/to” another component (e.g., a second component). When referred to as being “connected to,” it should be understood that any component may be directly connected to the other component or may be connected through another component (e.g., a third component). On the other hand, when a component (e.g., a first component) is said to be “directly connected” or “directly connected” to another component (e.g., a second component), It may be understood that no other component (e.g., a third component) exists between other components.

As used in this document, the expression “configured to” depends on the situation, for example, “suitable for,” “having the capacity to.” ," can be used interchangeably with "designed to," "adapted to," "made to," or "capable of." The term “configured (or set to)” may not necessarily mean “specifically designed to” in hardware. Instead, in some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "processor configured (or set) to perform A, B, and C" refers to a processor dedicated to performing the operations (e.g., an embedded processor), or by executing one or more software programs stored on a memory device. , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

Terms used in this document are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by a person of ordinary skill in the technical field described in this document. Among the terms used in this document, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this document, have an ideal or excessively formal meaning. It is not interpreted as In some cases, even terms defined in this document cannot be interpreted to exclude embodiments of this document.

Each feature of the various embodiments of the present invention can be partially or fully combined or combined with each other, and as can be fully understood by those skilled in the art, various technical interconnections and operations are possible, and each embodiment may be implemented independently of each other. It may be possible to conduct them together due to a related relationship.

For clarity of interpretation of this specification, terms used in this specification will be defined below.

Below, the stock item recommendation system will be described in detail with reference to the drawings.

1 is a schematic diagram of a stock item recommendation system according to an embodiment of the present invention. Referring to FIG. 1, the stock item recommendation system 1000 may be a system configured to recommend stocks with a high probability of investment success to a plurality of users 100 using publicly announced data provided by large institutions.

At this time, the disclosure data is data submitted quarterly to the U.S. Securities and Exchange Commission (SEC) on stock items invested and held by large institutions. Here, large institutions may be overseas hedge funds or institutions with assets of more than $100 million. . For example, the disclosed data may be Schedule 13F, and large institutions may be Warren Buffett's Berkshire Hair Corporation, Bridgewater Associates, etc.

The stock item recommendation system 1000 may include a plurality of user devices 100, a public data providing server 200, and a stock item recommendation server 300.

A plurality of user devices 100, a public data providing server 200, and a stock item recommendation server 300 that constitute the stock item recommendation system 1000 may be connected to each other through a network. Here, the network is, for example, a wired network such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), and ISDNs (Integrated Service Digital Networks), wireless LANs, CDMA, Bluetooth, It may encompass wireless networks such as Wi-Fi (Wireless Fidelity) and satellite communication, but the scope of the present invention is not limited thereto. Additionally, the network may transmit and receive information using short-range communication and/or long-distance communication. Here, short-range communication may include Bluetooth, RFID (Radio Frequency IDentification), Infrared Data Association (IrDA), UWB (Ultra-WideBand), ZigBee, and Wi-Fi technology, and long-distance communication may include CDMA. (Code Division Multiple Access), FDMA (Frequency Division Multiple Access), TDMA (Time Division Multiple Access), OFDMA (Orthogonal Frequency Division Multiple Access), and SC-FDMA (Single Carrier Frequency Division Multiple Access) technology.

A plurality of user devices 100 may receive recommended stock items provided by the stock item recommendation server 300. The plurality of user devices 100 are electronic devices used by a plurality of users and provide a user interface through which recommended stock items can be provided, for example, a smartphone, tablet PC (personal computer), laptop and/or It may include at least one of a PC, etc.

The public data provision server 200 may provide the stock item recommendation server 300 with public data necessary for recommending stock items. Although not shown in FIG. 1, the disclosure data providing server 200 may be connected to a network with hedge funds or institutions corresponding to large institutions, and the status of stock items held by each institution from each large institution is provided on a quarterly basis. A report can be provided. In various embodiments, the public data provision server 200 may be a web server that provides a web page related to a public data provision service according to a client's request, or a mobile web server that provides a mobile website. However, it is not limited to this. For example, the public data providing server 200 may be a web server that provides the U.S. Securities and Exchange Commission (SEC) site.

In an embodiment of the present invention, public data may include data provided by large institutions to the public data provision server 200 to data recently provided to the U.S. Securities and Exchange Commission.

The stock item recommendation server 300 may select recommended stock items using public data provided from the public data provision server 200 and provide the selected recommended stock items to a plurality of user devices 100 . The stock item recommendation server 300 may include a general-purpose computer, laptop, and/or data server that performs various calculations to recommend stock items suitable for investment. In various embodiments, the stock item recommendation server 300 may be a web server that provides a web page related to a stock item recommendation service or a mobile web server that provides a mobile website according to a client's request. However, it is not limited to this.

More specifically, the stock item recommendation server 300 divides stock items into value stocks and growth stocks and then analyzes the past investment styles of large institutions that provided public data to the public data provision server 200 to invest heavily in value stocks. institutions that are highly exposed to value investment, that is, institutions with high exposure to value investment, are selected, stocks commonly purchased by the selected institutions are selected using public data, and among the selected stocks, stocks that have fallen a lot during a preset period are given priority. can do. At this time, the preset period may be a period estimated as close as possible to the time when the relevant institution purchased the stock, taking into account the timing of the announcement of public data. For example, the pre-set period may be a period of more than 45 days and 3 months + 45 days or less because disclosure data is generally announced 45 days after the end of the quarter, but is not limited to this.

In an embodiment of the present invention, the method of distinguishing between value stocks and growth stocks is to use the value stock scores and growth stock scores announced by investment information companies or research companies, and to calculate percentages according to the respective directions of various indicators in financial statements and use them. Method, a method of applying supervised learning of machine learning to various indicators of financial statements, and a method of applying unsupervised learning of machine learning to various indicators of financial statements.

The stock item recommendation server 300 is shown as one server in FIG. 1 and explained as consisting of one server, but is not limited thereto, and includes a server for storing and transmitting and receiving information on recommended stock items and a server for recommending stock items. It may further include a server to provide an interface to the server.

The stock item recommendation server 300 may provide recommended stock items to a plurality of user devices 100.

The stock item recommendation server 300 may provide a stock item recommendation platform. Here, the stock item recommendation platform may mean a means of using services provided by the stock item recommendation server 300 in the form of a web page, smartphone application, or program through a network. Accordingly, the plurality of user devices 100 connected to the stock item recommendation server 300 and the network may be devices that can use or have the stock item recommendation platform installed.

In the following, the specific configuration of each of the plurality of user devices 100 among the components that make up the stock item recommendation system 1000 according to an embodiment of the present invention will be described in detail.

Figure 2 is a block diagram showing the configuration of a user device according to an embodiment of the present invention. Referring to FIG. 2 , each of the plurality of user devices 100 may include a memory interface 110, one or more processors 120, and a peripheral interface 130. Various components within the user device 100 may be connected by one or more communication buses or signal lines.

The memory interface 110 is connected to the memory 150 and can transmit various data to the processor 120. Here, the memory 150 is a flash memory type, hard disk type, multimedia card micro type, card type memory (for example, SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, It may include at least one type of storage medium among PROM, network storage, cloud, and blockchain database.

In various embodiments, the memory 150 includes an operating system 151, a communication module 152, a graphical user interface (GUI) 153, and the communication module 152 includes one or more other devices, computers, and servers. can communicate with at least one of A graphic user interface module (Graphic User Interface: GUI, 153) can process a graphic user interface. Sensor processing module 154 may process sensor-related functions (eg, processing voice input received using one or more microphones 192). The phone module 155 can process phone-related functions. Application module 156 may perform various functions of a user application, such as electronic messaging, web browsing, media processing, navigation, imaging, and other processing functions. In addition, each user device 100 may store one or more software applications (156-1, 156-2, for example, a stock item recommendation platform) associated with one type of service in the memory 150.

In various embodiments, the memory 150 may store a digital assistant client module 157 (hereinafter referred to as a DA client module), thereby storing instructions for performing client-side functions of the digital assistant and various user data 158, For example, user-customized vocabulary data, preference data, and other data such as the user's electronic address book, to-do list, shopping list, etc.) may be stored.

Meanwhile, the DA client module 157 uses various user interfaces provided in each user device 100, for example, the user's voice input, text input, touch input, and /Or gesture input may be obtained.

Additionally, the DA client module 157 can output data in audiovisual and tactile forms. For example, the DA client module 157 may output data consisting of a combination of at least two or more of voice, sound, notification, text message, menu, graphics, video, animation, and vibration. In addition, the DA client module 157 can communicate with a digital assistant server (not shown) using the communication subsystem 180.

In various embodiments, the DA client module 157 may collect additional information about the surrounding environment of each user device 100 from various sensors, subsystems, and peripheral devices to construct a context associated with each user input. You can. For example, the DA client module 157 may infer each user's intention by providing context information along with user input to the digital assistant server. Here, context information that may accompany each user input may include sensor information, for example, lighting, ambient noise, ambient temperature, images of the surrounding environment, video, etc. As another example, the context information may include the physical state of each user device 100 (e.g., device orientation, device location, device temperature, power level, speed, acceleration, motion pattern, cellular signal strength, etc.) there is. As another example, context information may include information related to the software status of each user device 100 (e.g., processes running on each user device 100, installed programs, past and present network activity, background services, errors, etc. logs, resource usage, etc.).

In various embodiments, memory 150 may include added or deleted instructions.

The processor 120 can control the overall operation of each user device 100 and execute various commands to provide recommended stock items by running an application or program stored in the memory 150. More specifically, in the case of each user device 100, the processor 120 may request the provision of information on recommended stock items or run a stock item recommendation application or program that can receive recommended stock items.

The processor 120 may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Additionally, the processor 120 may be implemented in the form of an integrated chip (IC) such as a system on chip (SoC) in which various computing devices such as a neural processing unit (NPU) are integrated.

The peripheral interface 130 can be connected to various sensors, subsystems, and peripheral devices to provide data so that each user device 100 can perform various functions. Here, what function each user device 100 performs may be understood as being performed by the processor 120.

The peripheral interface 130 may receive data from the motion sensor 160, the light sensor (or light sensor) 161, and the proximity sensor 162, through which each user device 100 can determine orientation, light, and It can perform proximity detection functions, etc. For another example, the peripheral interface 130 may receive data from other sensors 163 (positioning system-GPS receiver, temperature sensor, biometric sensor), and through this, each user device 100 may receive data from other sensors 163. Functions related to fields 163 can be performed.

In various embodiments, each user device 100 may include a camera subsystem 170 connected to the peripheral interface 130 and an optical sensor 171 connected thereto, through which each user device 100 may take a photo. and video clip recording.

In various embodiments, each user device 100 may include a communication subsystem 180 connected to the peripheral interface 130. The communication subsystem 180 consists of one or more wired/wireless networks and may include various communication ports, radio frequency transceivers, and optical transceivers.

In various embodiments, each user device 100 includes an audio subsystem 190 connected to a peripheral interface 130, and this audio subsystem 190 includes one or more speakers 191 and one or more microphones 192. By including, the user device 100 can perform voice-activated functions, such as voice recognition, voice duplication, digital recording, and phone functions.

In various embodiments, each user device 100 may include an input/output (I/O) subsystem 140 connected to a peripheral interface 130. For example, the I/O subsystem 140 may control the touch screen 143 included in each user device 100 through the touch screen controller 141. As an example, information for requesting the provision of recommended stock items can be entered through the touch screen, and it can be confirmed whether the recommended stock items and information related thereto are displayed. The touch screen controller 141 uses any one of a plurality of touch sensing technologies such as capacitive, resistive, infrared, surface acoustic wave technology, proximity sensor array, etc. to detect the user's contact and movement or interruption of the contact and movement. can be detected. As another example, the I/O subsystem 140 may control other input/control devices 144 included in each user device 100 through other input controller(s) 142. As an example, other input controller(s) 142 may control one or more buttons, rocker switches, thumb-wheels, infrared ports, USB ports, and pointer devices such as a stylus.

Figure 3 is a block diagram showing the configuration of a stock item recommendation server according to an embodiment of the present invention. Referring to FIG. 3, the stock item recommendation server 300 may include a communication interface 310, a memory 320, an input/output interface (I/O Interface) 330, and a processor 340, and each component is one. They can communicate with each other through one or more communication buses or signal lines.

The communication interface 310 can be connected to each of the plurality of user devices 100 and the public information providing server 200 through a wired/wireless communication network to exchange data. More specifically, the communication interface 310 can receive public disclosure data of large institutions from the public disclosure data provision server 200 and provide recommended stock items to each of the plurality of user devices 100.

The communication interface 310 includes a wired communication port 311 and a wireless circuit 312, and the wired communication port 311 is connected to one or more wired interfaces, such as Ethernet, Universal Serial Bus (USB), Firewire, etc. may include. Additionally, the wireless circuit 312 can transmit and receive data with an external device through RF signals or optical signals. Additionally, wireless communications may use at least one of a plurality of communication standards, protocols and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

The memory 320 can store various data used in the stock item recommendation server 300. For example, the memory 320 can store recommended stock items and related information provided to a plurality of user devices 100, and can store public disclosure data of large institutions provided from the public disclosure data provision server 200. , a function or algorithm that determines recommended stock items based on public data can be stored.

In various embodiments, memory 320 may include volatile or non-volatile recording media capable of storing various data, instructions, and information. For example, the memory 320 may be a flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage storage. , cloud, or blockchain database may include at least one type of storage medium.

In various embodiments, the memory 320 may store the configuration of at least one of the operating system 321, the communication module 322, the user interface module 323, and one or more applications 324.

An operating system (321, e.g., an embedded operating system such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) controls and manages common system tasks (e.g., memory management, storage device control, power management, etc.). It may include various software components and drivers for various hardware, firmware, and software components and may support communication between various hardware, firmware, and software components.

The communication module 323 may support communication with other devices through the communication interface 310. The communication module 320 may include various software components for processing data received by the wired communication port 311 or the wireless circuit 312 of the communication interface 310.

The user interface module 323 may receive a user's request or input from a keyboard, touch screen, microphone, etc. through the I/O interface 330 and provide a user interface on the display.

Applications 324 may include programs or modules configured to be executed by one or more processors 330 . Here, an application for providing a stock item recommendation method may be implemented on a server farm.

The application 324 may be software for buying, selling, or analyzing stocks and making recommendations based on this. For example, it could be a typical Home Trading System (HTS), or it could be a third-party application. The functions described below may operate as some functions of HTS.

The input/output (I/O) interface 330 may connect at least one of input/output devices (not shown) of the stock item recommendation server 300, such as a display, keyboard, touch screen, and microphone, to the user interface module 323. The I/O interface 330 may receive user input (eg, voice input, keyboard input, touch input, etc.) together with the user interface module 323 and process commands according to the received input.

The display 330 can output various interface screens provided by the stock item recommendation server 300. For example, display 330 may be a touch-sensitive display. A touch-sensitive display can provide an input interface and an output interface between the device and the user. As another example, display 330 may be a touch screen. The touch screen may include sensors that accept user input based on haptics and tactile contact. As another example, display 330 may be a sound display. If the stock item recommendation server 300 includes a sound display, sound can be output without a separate audio device.

The processor 340 is connected to the communication interface 310, memory 320, and I/O interface 330 to control the overall operation of the stock item recommendation server 300, and can control the application or Through the program, various commands can be executed to derive recommended stocks among multiple stock items.

The processor 340 may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Additionally, the processor 340 may be implemented in the form of an integrated chip (IC) such as a system on chip (SoC) in which various computing devices are integrated. Alternatively, the processor 340 may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

More specifically, the processor 340 may distinguish between value stocks and growth stocks using at least one of a program or algorithm that distinguishes between value stocks and growth stocks among a plurality of stock items. At this time, the method of distinguishing between value stocks and growth stocks is to use the value stock scores and growth stock scores announced by investment information companies or research companies, to calculate percentages according to each direction of various indicators in financial statements, and to use them. Considering various indicators, it can be distinguished using either a method of applying supervised learning of machine learning or a method of applying unsupervised learning of machine learning.

Additionally, the processor 340 can calculate value investment exposure scores of large institutions that provide publicly disclosed data. More specifically, the processor 340 can calculate a value investment exposure score based on past disclosure data stored in the memory 320 to determine whether a large institution's investment propensity is to invest in value stocks or growth stocks. At this time, the method of calculating the value investment exposure score is to calculate the weighted average in proportion to the trading volume of each record for each record held in the past through past disclosure data, regardless of the transaction volume for each record held in the past through past disclosure data. It can be either a simple average calculation method or a calculation method by varying the weights over time and giving more weight to recently held stocks.

In addition, the processor 340 can calculate the value investment attractiveness of each stock item based on the value investment exposure scores of large institutions when public disclosure data of large institutions is released each quarter. More specifically, the processor 340 determines the scope of application among a plurality of stock items, and purchases the target stock for which the attractiveness score is calculated among the stock items corresponding to the set application range from a large institution through public disclosure data from the previous quarter or existing stock items. After selecting stock items that have increased their proportions, you can calculate the attractiveness of value investment for the selected items. At this time, the method of calculating the value investment attractiveness of each stock item can be calculated by adding up the value investment exposure scores of the large institutions holding the stock for the selected stock items and then dividing by the total number of institutions. In addition, the processor 340 may assign additional weight by considering the proportion of each large institution's newly purchased stocks in the large institution's operating scale. Additionally, the processor 340 may assign weights by considering the expertise and skill level of each large institution for the sector to which the stock item belongs.

The processor 340 calculates the value investment attractiveness of some of the stock items among the plurality of stock items, selects the top items within a preset range, and finally selects the stock items that have fallen for a preset period. It can be recommended to buy. Here, the preset period can be estimated to be as close as possible to the time when large institutions purchased the selected stock items, taking into account the timing of the announcement of public data. For example, if the disclosure data is announced 45 days after the end of each quarter, the preset period may usually be a period of 45 days or more and 3 months + 45 days or less.

The stock item recommendation system according to the embodiment of the present invention configured in this way is based on the stock item recommendation server 300 provided with public disclosure data related to the status of stock items held by large overseas institutions from the public data provision server 200. By recommending stock items to multiple user devices 100, multiple users can easily invest in overseas stocks and secure a greater safety margin for investment.

Next, the stock item recommendation method according to an embodiment of the present invention will be examined in more detail with reference to FIGS. 4 and 5.

Figure 4 is a flowchart sequentially showing a stock item recommendation method according to an embodiment of the present invention. Figure 5 is a flowchart showing the process of calculating investment attractiveness for each stock item according to an embodiment of the present invention. The stock item recommendation method according to the embodiment of the present invention related to FIGS. 4 and 5 may be performed by the processor 340 of the stock item recommendation server 300. For convenience of explanation, it is performed by the stock item recommendation server 300. Let's assume that you do and explain.

Referring to FIG. 4, the stock item recommendation server 300 divides stocks listed on the market into value stocks and growth stocks (S410). More specifically, the stock item recommendation server 300 can classify stocks listed on the market by listing them as continuous values from 0 to 100, rather than dichotomously, such as value stocks or growth stocks. For example, the stock item recommendation server 300 scores stocks listed on the market with a number between 0 and 100, and then classifies those with scores between 1 and 50 as growth stocks and those with scores between 51 and 100 as value stocks. .

In step 410, one of the methods by which the stock item recommendation server 300 scores the stocks listed on the market is the value stock score (e.g., Morningstar, etc.) announced by an investment information company (e.g., Morningstar, etc.) There are ways to use the Value Score and Growth Score.

In addition, another method of scoring stocks listed on the market in the stock item recommendation server 300 is various indicators of financial statements (e.g., PER, PBR, dividend rate, profit growth rate, cash flow growth rate) There is a method of calculating percentages according to each direction and then using the average of the percentages of each calculated indicator. For example, in the case of PER, a percentage is calculated by listing the PER values of stocks listed on the market, then 1 point is given to stocks in the top 1% of PER values, 85.5 points are given to stocks in the bottom 14.5%, and so on. , after calculating all various indicators other than PER, the final score can be calculated by simple averaging or weighted average of the percentages of various indicators. At this time, in the case of PER, the closer it is to 100, the more likely it is to be a value stock.

In addition, another method of scoring stocks listed on the market in the stock item recommendation server 300 is to use various indicators of financial statements (e.g., PER, PBR, dividend rate, profit growth rate, cash flow) There is a way to apply supervised learning of machine learning (growth rate, etc.). More specifically, the method of determining weights by applying supervised machine learning is to first have experts select stocks that are clearly judged to be value stocks and stocks that are clearly judged to be growth stocks, and then convert these into labeled data. This is a method of learning the classification algorithm. At this time, the independent variable can be various indicators of financial statements, the dependent variable can be a value stock and/or growth stock category, and the parameter to be learned can be a weight for each variable. Here, the stock item recommendation server 300 may use the value obtained by multiplying the probability of a value stock derived by a learned machine learning algorithm by 100 as the score.

In addition, another method of scoring stocks listed on the market in the stock recommendation server 300 is to divide stocks into two groups through unsupervised machine learning and determine representative stocks of each group. One group is value stocks and the other group is growth stocks, and then the closer to the central coordinates of each group, the higher the characteristic is considered to be scored.

Next, the stock item recommendation server 300 calculates the value investment exposure for each institution providing public information (S420). More specifically, the stock item recommendation server 300 can calculate whether the investment style is a value stock investment style or a growth stock investment style based on past stock records held by institutions providing public information. More preferably, the stock item recommendation server 300 can calculate whether institutions providing public information are close to the value stock investment style. In other words, whether institutions are close to the value stock investment style can be considered as value investment exposure. At this time, stock records held by institutions in the past may be stored in the memory 320.

In step 420, one of the methods by which the stock item recommendation server 300 calculates the value investment exposure for each institution is a weighted average in proportion to the trading volume of each record for each record held in the past, or a simple average regardless of the trading volume. There is. For example, when classifying value stocks and growth stocks in step 410, assuming that the value stock classification scores for stocks A, B, and C are 80 points, 50 points, and 20 points, respectively, AA institutions have previously divided stock A into 100 shares twice, If Stock B held 50 shares once and Stock C held 1,000 shares once, if the trading volume weighted average method was followed, the investment style score of AA institutions would be (80 x 100 + 80 x 100 + 50 x 50 + 20 x 1000) / (100 + 100 + 50 + 1000) = 30.8 points, and if you follow the simple average method regardless of trading volume, it can be (80+80+50+20+/4=57.5 points.

In addition, among the methods of calculating value investment exposure by institution in the stock item recommendation server 300, another method is to vary the weighting over time and place more weight on recently held stocks. A method of calculating the weight by varying the weight over time and giving more weight to recently held stocks can be calculated using [Equation 1] below.

Here, S is the value investment exposure score for each quarter, and n is the number of how many quarters of data to consider. For example, if data from the past 20 quarters is considered, the value of n can be 20. In addition, a is a decay factor and has a value greater than 0 or less than 1. If 1, the same weight is given regardless of the point in time it was held, and if it is less than 1, a lower weight is given to the past holding record. will be.

More specifically, the stock item recommendation server 300 multiplies each quarter's value investment exposure by the multiplier of a, which is the decay factor, gives more weight to the more recent times, adds them (denominator), and sums all weights a of 1. Divide it so that it becomes (molecules). As a result of calculating an institution's value investment exposure by varying the weight over time, an institution that held a lot of growth stocks in the past but has recently invested a lot in value stocks can be calculated to be close to the value investor style.

Next, the stock item recommendation server 300 receives quarterly public disclosure data announced by large institutions from the public disclosure data provision server 200 (S430). In the embodiment of the present invention, the disclosure data receiving step (S430) is described as after calculating the institution's value investment exposure, but it is not limited to this. For example, the disclosure data receiving step (S430) may receive stocks listed on the market in advance before classifying them into value stocks and growth stocks.

Next, the stock item recommendation server 300 calculates the value investment attractiveness of each stock item based on the value investment exposure score and public data for each institution calculated in step 420 (S440). Referring to FIG. 5, the method of calculating value investment attractiveness may include an institutional unit selection step (S441), a target stock selection step (S442), and a value investment attractiveness calculation step (S443).

The institution-level selection step (S441) may be a step of selecting whether to calculate the value investment attractiveness based on the disclosed data of any of the institutions that provide disclosed data to calculate the value investment attractiveness for each stock item. In the institution-level selection step (S441), all institutions that provide disclosure data can be selected, only institutions with a high value stock investment style score among the value investment exposure scores for each institution calculated in step 420, or only specific preset institutions can be selected. there is. Here, when selecting only institutions with a high value stock investment exposure (or style) score among the value investment exposure scores for each institution calculated in step 420, institutions that fall within a preset range can be selected. Institutions that fall within a preset range may be selected, for example, to select only institutions with a value stock investment exposure score of more than 10% for each institution or to select only the top 5 institutions. Alternatively, institutions that fall within a pre-set scope can pre-set only specific institutions among those that provide public disclosure data.

In the target stock selection step (S442), institutions selected in the institutional unit selection step (S441) can select newly purchased stock items and stock items with an increased proportion than the existing holdings from the last quarter's public disclosure data.

The value investment attractiveness calculation step (S443) calculates the value investment attractiveness of each stock item selected in the target stock selection step (S442). At this time, value investment attractiveness can be calculated using one of the first to fourth methods.

The first method can calculate the value investment attractiveness of each stock using the following [Equation 2]. More specifically, the first method is to select institutions that purchased the stock for each of the stock items selected in step 442, add the value investment exposure scores, and then divide by the total number of institutions.

Here, n is the total number of institutions within the target range, k has a value of 1 if the i-th institution purchased the stock and 0 if it did not, and s is the investment style score of the i-th institution.

The second method can calculate the attractiveness of value investment using the following [Equation 3]. More specifically, the second method selects the institutions that purchased the stock item for each of the stock items selected in step 442, adds the value investment exposure score, and calculates the amount of new purchases of the stock item by each institution. Alternatively, the amount of increased holdings of the relevant stock item is given additional weight considering its proportion in the institution's operating scale and then divided by the total number of institutions. In other words, in the second method, in [Equation 2], additional weight is given to the amount of each institution's new purchase of the relevant stock item or the amount of increased holding of the relevant stock item, taking into account the proportion of the institution's operating scale. It's a method.

Here, w represents the proportion of the stocks purchased by the ith institution in the total operating scale. For example, if a 1 trillion won institution newly purchases 50 billion won worth of stocks, the w value may be 0.05.

The third method can calculate the attractiveness of value investment using the following [Equation 4]. More specifically, the third method is to select the institutions that purchased the stock items for each of the stock items selected in step 442, add up the value investment exposure scores, and then calculate each institution's expertise in the sector to which the stock belongs. This is a method of giving additional weight considering skill level and then dividing by the total number of organizations. In other words, the third method is a method that gives additional weight in [Equation 2] by considering each institution's expertise and skill level for the sector to which the stock belongs. At this time, a method for calculating expertise and skill level may include, but is not limited to, a method that considers past win rates and/or returns for stocks in the sector.

Here, t may be a number standardized to a value between 0 and 1 by measuring the rate of return and/or win rate that the ith institution achieved by investing in stocks in the sector to which the stock belongs in the past. For example, if you made a profit 8 out of 10 times you invested in that sector, the t value could be 0.8. In addition, other methods can be used to quantify an institution's skills in a given sector.

The fourth method can calculate the attractiveness of value investment using the following [Equation 5]. More specifically, the fourth method selects the institutions that purchased the stock item for each of the stock items selected in step 442, adds the value investment exposure score, and calculates the amount of new purchases of the stock item by each institution. Alternatively, the amount of increased holding of the stock in question is calculated by taking into account the proportion of the institution's operating scale, giving additional weight considering each institution's expertise and skill level in the sector to which the stock belongs, and dividing it by the total number of institutions. It's a method.

Next, the stock item recommendation server 300 intermediately selects stock items to recommend for purchase (S450). At this time, the stock item recommendation server 300 may intermediately select stock items to recommend for purchase according to a preset upper standard (m) as a result of the attractiveness calculation. Here, the preset upper standard (m) can select the top m stocks with attractiveness scores or select the stocks with the top m%. Additionally, the stock item recommendation server 300 may select all stocks whose attractiveness score as a result of attractiveness calculation is greater than or equal to a preset specific value.

Next, the stock item recommendation server 300 finally selects a stock item to recommend for purchase among the intermediately selected stock items to recommend for purchase (S460). Here, in the final selection stage of stock items to recommend for purchase, stock items that have fallen for a preset period (n) can be finally selected. At this time, the preset period (n) can be estimated and set as close as possible to the time when the relevant institution purchased the stock item to be finally recommended for purchase, taking into account the timing of the announcement of public data. For example, Schedule 13F, which is generally disclosed data, is disclosed 45 days after the end of the quarter, so the preset period (n) may be 45 days or more and 3 months + 45 days or less.

Subsequently, when the stock item recommendation server 300 transmits the finally selected stock items recommended for purchase to the plurality of user devices 100, the stock item recommendation method according to the embodiment of the present invention is completed.

In this way, the stock item recommendation method according to the embodiment of the present invention recommends stock items to be purchased to multiple users using public data submitted by institutions with assets of $100 million or more, thereby securing a safety margin for multiple users. and enable the purchase of overseas stocks at good prices.

Although embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be modified and implemented in various ways without departing from the technical spirit of the present invention. there is. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

100: plural first user devices
110: memory interface 120: processor
130: peripheral interface 140: I/O subsystem
141: Touch screen controller 142: Other input controller
143: touch screen
144: Other input control devices
150: Memory 151: Operating system
152: Communication module 153: GUI module
154: sensor processing module 155: phone module
156: Applications
156-1, 156-2: Application
157: Digital assistant client module
158: User data
160: motion sensor 161: light sensor
162: Proximity sensor 163: Other sensors
170: Camera subsystem 171: Optical sensor
180: Communication subsystem
190: Audio subsystem
191: Speaker 192: Microphone
200: Public data provision server
300: Stock item recommendation server
310: communication interface
311: wired communication port 312: wireless circuit
320: memory
321: operating system 322: communication module
323: user interface module 324: application
330: I/O interface 340: Processor

Claims (15)

A stock item recommendation method implemented by a processor,
Classifying stocks listed on the market into value stocks and growth stocks;
Calculating value investment exposure for each institution providing public disclosure data;
Calculating value investment attractiveness for each stock item using the value investment exposure calculation result for each institution and the public information;
A step of intermediately selecting stock items that satisfy a preset upper standard as a result of calculating the value investment attractiveness of each stock item; and
A method of recommending stock items, including the step of finally selecting stock items that are in a declining state in a preset period among the intermediately selected stock items. The method of claim 1, wherein the step of dividing into value stocks and growth stocks is:
A stock recommendation method that grades stocks listed on the market with a number between 0 and 100 and classifies them into value stocks and growth stocks. According to clause 2,
The method for scoring stocks listed on the market is:
Investment information A method of using the Value Score and Growth Score announced by the company is to calculate the percentage of various indicators in the financial statements according to each direction, and then calculate the average of the percentage of each calculated indicator. A method of using, a method of applying supervised learning of machine learning to various indicators of financial statements, and a method of dividing stocks into two groups through unsupervised learning of machine learning and identifying the representative stocks of each group to determine one group. A stock item recommendation method that uses one of the following methods: one group is value stocks, and another group is growth stocks, and the closer to the center coordinates of each group, the higher the corresponding characteristic. The method of claim 3, wherein the method using supervised learning of machine learning,
A step of selecting stocks judged to be value stocks and stocks judged to be growth stocks by experts and then setting them as labeled data; and
A stock item recommendation method comprising: learning a classification algorithm based on the labeled data. The method of claim 1, wherein the step of calculating the value investment exposure for each institution providing the disclosed data is:
A stock item recommendation method that calculates whether the investment style is a value stock investment style or a growth stock investment style based on past stock records held by institutions providing the above-mentioned disclosure data. The method of claim 5, wherein the step of calculating the value investment exposure for each institution providing the disclosed data is:
For each record held in the past by the institution providing the above-mentioned disclosure data, a weighted average is calculated in proportion to the trading volume of each record, or a simple average is calculated regardless of the trading volume, and the weight is varied according to the passage of time to add more weight to recently held stocks. A stock item recommendation method that is calculated using one of the weighted calculation methods. The method of claim 1, wherein the step of calculating the value investment attractiveness for each stock item is:
An institution range selection step of selecting whether to calculate value investment attractiveness based on the disclosed data of any of the institutions providing the disclosed data;
A target stock selection step in which the institutions selected in the above institutional range selection step select newly purchased stock items and stock items with an increased proportion compared to the existing holdings from the last quarter's public disclosure data; and
A stock item recommendation method comprising a value investment attractiveness calculation step of calculating value investment attractiveness for the stock items selected in the target stock selection step. The method of claim 7, wherein the value investment attractiveness calculation step is,
A first method is to select institutions that purchased the stock items for each of the stock items selected in the target stock selection step, add up the value investment exposure scores, and then divide by the total number of institutions, the selected institutions in the target stock selection step For each stock item, the institutions that purchased the stock item are selected and the value investment exposure score is added, and the amount that each institution newly purchases the relevant stock item or increases its holdings of the relevant stock item is calculated by the relevant institution. The second method is to add additional weight considering the proportion of the management scale and divide by the total number of institutions. For each stock selected in the target stock selection step, the value investment exposure is calculated by selecting the institutions that purchased the stock. A third method is to add up the scores, give additional weight considering the expertise and skill level of each institution in the sector to which the stock belongs, and then divide by the total number of institutions, and each of the stock items selected in the target stock selection step. After selecting the institutions that purchased the relevant stock item and adding up the value investment exposure scores, the amount that each institution newly purchased the relevant stock item or increased its holdings of the relevant stock item is calculated based on the institution's operating scale. A stock item recommendation method that is calculated using any one of the fourth methods, which takes into account the proportion, gives additional weight considering the expertise and skill level of each institution in the sector to which the stock belongs, and then divides by the total number of institutions. The method of claim 1, wherein in the final selection of the stock items,
A stock item recommendation method in which the preset period is set by estimating as close as possible the time when the institution purchased the final selected stock item, taking into account the timing of the announcement of the public data. A stock item that selects recommended stock items using public data published quarterly on stock items held by institutions with assets of over $100 million and provides a stock recommendation platform to provide selected recommended stock items to external parties. Recommended Server; and
A stock item recommendation system comprising: a plurality of user devices on which the stock item recommendation platform is installed and which receive recommended stock items from the stock item recommendation server through the stock item recommendation platform. The method of claim 10, wherein the stock item recommendation server,
a communication interface that receives the public information and transmits the recommended stock items to an external party;
A memory that stores a program or algorithm for selecting public data released by the above-mentioned institutions and the recommended stock items; and
It operates in connection with the memory, divides stocks listed on the market into value stocks and growth stocks, calculates the value investment exposure for each institution providing the disclosure data, and then calculates the value investment exposure calculation results for each institution and the disclosure data. The value investment attractiveness of each stock item is calculated, and as a result of the value investment attractiveness calculation for each stock item, the stock items that satisfy the preset upper standards are selected, and among the selected stock items, those that are in a decline during a preset period are selected. A stock item recommendation system that includes a processor that ultimately selects and recommends stock items. The method of claim 11, wherein the processor:
Investment information A method of using the Value Score and Growth Score announced by the company is to calculate the percentage of various indicators in the financial statements according to each direction, and then calculate the average of the percentage of each calculated indicator. A method of using, a method of applying supervised learning of machine learning to various indicators of financial statements, and a method of dividing stocks into two groups through unsupervised learning of machine learning and identifying the representative stocks of each group to determine one group. One group is value stocks, and the other group is growth stocks. Then, the stocks listed on the market are scored using one of the methods that considers that the closer to the center coordinate of each group, the higher the characteristic is, and the value stocks are classified into the value stocks. A stock recommendation system that categorizes the above growth stocks. The method of claim 11, wherein the processor:
For each record held in the past by the institution providing the above-mentioned disclosure data, a weighted average or simple average is calculated in proportion to the trading volume of each record, and the weight is varied according to the passage of time, giving more weight to recently held stocks. A stock item recommendation system that calculates whether the institution has a value stock investment style or a growth stock investment style by any one of the following methods. The method of claim 11, wherein the processor:
Select whether to calculate value investment attractiveness based on the disclosed data of any of the institutions providing the above-mentioned public data, and select the selected institutions based on the newly purchased stock items and the proportion increased from the existing holdings in the last quarter's public data. A stock item recommendation system that selects stock items with and then calculates the attractiveness of value investment for the selected stock items. 15. The method of claim 14, wherein the processor:
For each of the selected stock items, the institutions that purchased the stock item are selected and the value investment exposure scores are added, and the summed value is added to the amount of new purchases of the relevant stock item by each institution or the amount of the relevant stock item. After calculating the value investment attractiveness, the amount of increased holding is weighted by considering the proportion of the institution's operating scale or by considering the expertise and skill level of each institution in the sector to which the stock belongs. A stock recommendation system divided by the total number of institutions.

Images