Stock price evaluation device, stock price evaluation program, stock price monitoring program, asset management program, stock price evaluation method, stock price monitoring method, and asset management method

Abstract

To provide a stock price evaluation device capable of calculating and evaluating an intrinsic asset value, a stock price evaluation program, a stock price monitoring program, an asset management program, a stock price evaluation method, a stock price monitoring method, and an asset management method.SOLUTION: In the stock price evaluation device, a control unit 10 comprises: a machine learning unit 100 which estimates a dynamics function common to a plurality of companies by machine learning of relations between company financial information in a plurality of periods of the plurality of companies and asset prices; an intrinsic value calculation unit 110 which calculates intrinsic values of assets in accordance with the dynamics function estimated by the machine learning unit 100; a value difference calculation unit 120 which calculates differences between the intrinsic values calculated by the intrinsic value calculation unit 110 and the asset prices as crowd psychology; and an asset management unit 130 which specifies undervalued stocks and overvalued stocks by the crowd psychology calculated by the value difference calculation unit 120.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention particularly relates to a stock price evaluation device, a stock price evaluation program, a stock price monitoring program, an asset management program, a stock price evaluation method, a stock price monitoring method, and an asset management method relating to the evaluation, monitoring, and management of stock prices. [Background technology]

[0002] With the recent development of ICT (Information and Communication Technology), there has been a growing trend to apply artificial intelligence to financial operations. In particular, technological innovation is progressing in the field of financial engineering, known as FinTech, which combines finance and IT (Information Technology).

[0003] Patent Document 1 describes a conventional stock price prediction system that is characterized by having a prediction set acquisition means for acquiring a set of stock price prediction values ​​based on input data indicating factors that change stock prices, and a collective intelligence acquisition means for acquiring collective intelligence of stock prices with high prediction accuracy from the set of stock price prediction values. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-200513 [Non-patent literature]

[0005] [Non-Patent Document 1] JAOhlson, “Earning, Book Values, and Dividends in Eq-uity Valuation: An Empirical Perspective”, 2001, Contemporary Accounting Research, vol.18, no.1, p.107-120. Summary of the Invention [Problem to be solved by the invention]

[0006] However, there has been a technical demand for calculating an intrinsic asset value, which is a more realistic theoretical stock price than the technology of Patent Document 1, and evaluating the difference between this and the asset price, which is the actual stock price.

[0007] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a stock price evaluation device that solves the above-mentioned problems. [Means for solving the problem]

[0008] The stock price evaluation device of the present invention comprises a machine learning unit that performs machine learning on the relationship between financial information of a plurality of companies over a plurality of periods and asset prices and estimates a dynamics function common to the plurality of companies; an intrinsic value calculation unit that calculates the intrinsic value of an asset using the dynamics function estimated by the machine learning unit; and a value difference calculation unit that calculates the difference between the intrinsic value calculated by the intrinsic value calculation unit and the asset price as herd psychology. The value difference calculation unit draws a list of the crowd psychology based on the period and the type of stock. It is characterized by: The stock price evaluation device of the present invention is characterized in that the machine learning unit also uses, in the machine learning, performance forecasts by management or analysts indicated in the financial results summary. The stock price evaluation device of the present invention is characterized in that the dynamics function is an extension of the OVM model (Ohlson Valuation Model) to a nonlinear model. The stock price evaluation device of the present invention is characterized in that the value difference calculation unit detects abnormal stock prices based on the crowd psychology. 。 The stock price evaluation device of the present invention is characterized by further comprising an asset management unit that identifies undervalued stocks and overvalued stocks based on the herd psychology calculated by the value difference calculation unit. The stock price evaluation device of the present invention is characterized in that the asset management department manages a portfolio by going long on the undervalued stocks and short on the overvalued stocks. The stock price evaluation program of the present invention is a stock price evaluation program executed by a stock price evaluation device, which performs machine learning on the relationship between financial information of a plurality of companies over a plurality of periods and asset prices, estimates a dynamics function common to the plurality of companies, calculates the intrinsic value of assets using the estimated dynamics function, and calculates the difference between the calculated intrinsic value and the asset price as crowd psychology. , based on the period and type of stock, the crowd psychology is displayed in a list. Characterized by 。 The asset management program of the present invention program Based on the crowd psychology calculated by the above, undervalued stocks and overvalued stocks are identified, and the identified undervalued stocks are long-term and overvalued stocks are short-term managed as a portfolio. The stock price evaluation method of the present invention is a stock price evaluation method executed by a stock price evaluation device, which performs machine learning on the relationship between financial information of a plurality of companies over a plurality of periods and asset prices, estimates a dynamics function common to the plurality of companies, calculates an intrinsic value of assets using the estimated dynamics function, and calculates the difference between the calculated intrinsic value and the asset price as herd psychology. and then, based on the period and the type of stock, the herd psychology is displayed in a list. It is characterized by: The stock price monitoring method of the present invention is characterized in that abnormal stock prices are monitored based on the crowd psychology calculated by the stock price evaluation method. The asset management method of the present invention is characterized in that it identifies undervalued stocks and overvalued stocks based on the herd psychology calculated by the stock price valuation method, and manages a portfolio by going long on the identified undervalued stocks and short on the identified overvalued stocks. [Effects of the Invention]

[0009] According to the present invention, a stock price evaluation device can be provided that can calculate the intrinsic asset value and evaluate the difference from the asset price by performing machine learning on the relationship between the financial information of multiple companies over multiple periods and their asset prices, estimating a dynamics function, calculating the intrinsic value of the asset using the estimated dynamics function, and calculating the difference between the intrinsic value and the asset price as crowd psychology. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a control configuration of a stock price evaluation device according to an embodiment of the present invention. [Figure 2] 1 is a flowchart of a stock price evaluation process according to an embodiment of the present invention. [Figure 3] FIG. 3 is a conceptual diagram of the stock price evaluation process shown in FIG. 2. [Figure 4] FIG. 3 is a conceptual diagram of the list drawing process shown in FIG. 2. [Figure 5] 1 is a graph showing the correlation between the estimated intrinsic value ^Vi,t and the realized asset price Pi,t according to an embodiment of the present invention. [Figure 6] 10 is a graph showing the average value and standard deviation of the deviation rate ξi,t according to an example of the present invention. [Figure 7] 10 is a graph showing the average value and standard deviation of the deviation rate ξi,t after correction according to an embodiment of the present invention. [Figure 8] 1 is a graph showing the importance of explanatory variables according to an example of the present invention. [Figure 9] 1 is a graph showing cumulative returns of a long portfolio and a short portfolio according to an embodiment of the present invention. [Figure 10] 1 is a graph showing cumulative active returns of a long portfolio for each quantile according to an embodiment of the present invention. [Figure 11] 1 is a graph showing cumulative returns of a long-short portfolio according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] <Embodiment> [Configuration of stock price evaluation device 1] First, with reference to FIG. 1, the control configuration of a stock price evaluation device 1 according to an embodiment of the present invention will be described. The stock price evaluation device 1 is an information processing device for evaluating stock prices, such as a PC (Personal Computer), a server, a general-purpose computer, or a smartphone.

[0012] The stock price evaluation device 1 includes a control unit 10, an image processing unit 11, a memory unit 12, an input unit 13, a display unit 14, and a transmission / reception unit 15. Each unit is connected to the control unit 10 directly or via a bus, and the operation thereof is controlled by the control unit 10.

[0013] The control unit 10 is an information processing unit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), or an ASIC (Application Specific Integrated Circuit). The control unit 10 reads out a control program stored in the ROM or HDD of the storage unit 12, expands the control program into RAM, and executes it to operate as each part of the functional blocks described below. The control unit 10 also controls the entire device in accordance with predetermined instruction information input from an input unit 13 or an external terminal (not shown).

[0014] The image processing unit 11 is a control and calculation means including a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field-Programmable Gate Array), etc. The image processing unit 11 may function as a machine learning accelerator.

[0015] The storage unit 12 is a non-transitory recording medium such as a semiconductor memory such as a ROM (Read Only Memory) or a RAM (Random Access Memory) or a HDD (Hard Disk Drive). The ROM and HDD of the storage unit 12 store an OS (Operating System) for controlling the operation of the stock price evaluation device 1, various programs including application software (hereinafter simply referred to as "applications"), and various data. In addition, the storage unit 12 may also store user account settings.

[0016] The transmitter / receiver 15 is a network connection unit including a LAN (Local Area Network) board for connecting to an external network, a wireless LAN (WiFi) board, a Bluetooth (registered trademark) or short-range wireless radio transmitter / receiver, etc. The external network in this embodiment is, for example, an intranet such as a LAN, a WAN (Wide Area Network), or a mobile phone network. Furthermore, the transmitting / receiving unit 15 may be capable of connecting to various devices via a USB (Universal Serial Bus) or the like.

[0017] The input unit 13 is an input device including a keyboard, a pointing device, etc. The pointing device of the input unit 13 may be, for example, a mouse, a touch panel, a touch pad, an electromagnetic digitizer, etc. The input unit 13 acquires various instructions from the user.

[0018] The display unit 14 is an LCD (Liquid Crystal Display), an organic EL (Organic Electro-Luminescence) display, etc. The display unit 14 displays various types of information in a GUI (Graphical User Interface) or a CUI (Character-based User Interface). Furthermore, the input unit 13 and the display unit 14 may be integrally formed, such as a touch panel display.

[0019] In the stock price evaluation device 1, the control unit 10 and the image processing unit 11 may be integrally formed, such as in a CPU with a built-in GPU, a chip-on-module package, or a SOC (System On a Chip). Furthermore, the control unit 10 and the image processing unit 11 may have built-in RAM, ROM, flash memory, or the like. Furthermore, the stock price evaluation device 1 may be connected to a printer or the like for printing out various evaluation results and the like.

[0020] Next, the functional configuration of the stock price evaluation device 1 will be described. The control unit 10 of the stock price evaluation device 1 includes a machine learning unit 100, an intrinsic value calculation unit 110, a value difference calculation unit 120, and an asset management unit . The storage unit 12 stores financial asset forecast data 200 , model data 210 , intrinsic value data 220 , monitoring data 230 , management data 240 , a stock price evaluation program 300 , a stock price monitoring program 310 , and an asset management program 320 .

[0021] The machine learning unit 100 performs machine learning on the relationship between financial information and asset prices of multiple companies over multiple periods, and estimates a dynamics function common to the multiple companies. In this embodiment, the machine learning unit 100 may use, in machine learning, performance forecasts by management or analysts indicated in the financial results summary. Furthermore, in this embodiment, the dynamics function may be an extension of the Ohlson Valuation Model (OVM model) described in Non-Patent Document 1 to a non-linear model.

[0022] The intrinsic value calculation unit 110 calculates the intrinsic value of the asset using the dynamics function estimated by the machine learning unit 100.

[0023] The value difference calculation unit 120 calculates the difference between the intrinsic value calculated by the intrinsic value calculation unit 110 and the asset price as herd psychology. Additionally, in this embodiment, the value difference calculation unit 120 can also detect abnormal stock prices based on crowd psychology. In this case, the value difference calculation unit 120 can draw a list of crowd psychology based on the period and type of stock, and generate monitoring data 230.

[0024] The asset management unit 130 identifies undervalued stocks and overvalued stocks based on the herd psychology calculated by the value difference calculation unit 120. Specifically, in this embodiment, the asset management unit 130 can manage a portfolio by going long on undervalued stocks and short on overvalued stocks.

[0025] The financial asset forecast data 200 is data on stock prices, financial information used for corporate evaluation (financial data, panel data), and other data acquired from a so-called cloud server via an external network. In this embodiment, the financial asset forecast data 200 also includes performance forecasts by management or analysts shown in the financial results summary.

[0026] The model data 210 is data of a model learned by machine learning. Specifically, in this embodiment, data of a model calculated as a dynamics function F in machine learning may be stored. Furthermore, the model data 210 may be retrained by acquiring actual market data, as described below.

[0027] The intrinsic value data 220 is data that indicates the calculated intrinsic value of an asset and herd psychology. Specifically, in this embodiment, the intrinsic value data 220 may include data on theoretical stock prices for each company. Furthermore, the intrinsic value data 220 may include, as herd psychology, a PIR index that indicates the dissociation between the current stock price and the theoretical stock price, which will be described in detail in an embodiment below. In these cases, the intrinsic value data 220 may be a database that stores the current stock price, theoretical stock price, and PIR index for each stock.

[0028] The monitoring data 230 is image data or database data that shows a list of crowd psychology based on a period and a type of stock. The monitoring data 230 may be viewable and searchable, for example, from a web browser or a dedicated program.

[0029] The management data 240 is data on each stock used in portfolio management by the asset management unit 130. This management data 240 includes, for example, each stock for short and long management as described below, and may be dynamically set based on actual market data.

[0030] The stock price valuation program 300 is an application mainly used for machine learning, calculation of intrinsic value, and calculation of crowd psychology. The stock price valuation program 300 may be executed periodically by, for example, a task manager or "CRON."

[0031] The stock price monitoring program 310 is an application that detects abnormal stock prices based on crowd psychology and displays a list of crowd psychology. The stock price monitoring program 310 may be executed periodically in accordance with the execution of the stock price evaluation program 300, or may be executed on demand by a user. Furthermore, if an abnormal stock price is detected, a warning or the like may be sent to the user.

[0032] The asset management program 320 is an application for asset management. The asset management program 320 may be executed periodically or at the user's request for stock price evaluation.

[0033] Here, the control unit 10 of the stock price evaluation device 1 is made to function as a machine learning unit 100, an intrinsic value calculation unit 110, a value difference calculation unit 120, and an asset management unit 130 by executing the stock price evaluation program 300, the stock price monitoring program 310, and the asset management program 320 stored in the memory unit 12. Furthermore, the image processing unit 11 can be used as an accelerator or the like when the machine learning unit 100, the intrinsic value calculation unit 110, the value difference calculation unit 120, and the asset management unit 130 perform various calculations. Furthermore, each unit of the above-described stock price evaluation device 1 serves as a hardware resource for executing the stock price evaluation method, stock price monitoring method, and asset management method of the present invention. Note that a part or any combination of the above-described functional configurations may be configured in terms of hardware or circuits using ICs, programmable logic, FPGAs, or the like.

[0034] [Stock price evaluation process by stock price evaluation device 1] Next, the stock price evaluation process performed by the stock price evaluation device 1 according to the embodiment of the present invention will be described with reference to FIGS. In the stock price evaluation process of this embodiment, machine learning is used to separate theoretical stock prices from herd psychology. That is, the current stock price is calculated by adding the true value (fundamental value) that is the theoretical stock price to the value of herd psychology. Then, the deviation between this theoretical stock price and the actual stock price is monitored, stocks with abnormal stock prices are monitored, and risk assessment of the entire stock market, portfolio management, etc. are performed. In the stock price evaluation process of this embodiment, the control unit 10 mainly executes each program stored in the storage unit 12 in cooperation with each unit, using hardware resources. The stock price evaluation process will be described in detail below for each step with reference to the flowchart in FIG.

[0035] (Step S101) First, the machine learning unit 100 performs machine learning processing. The machine learning unit 100 obtains financial information such as net profits and forecast dividends for multiple periods for multiple companies, as well as asset prices such as current stock prices, from a server on the cloud via an external network, and stores them in financial asset forecast data 200. Then, the machine learning unit 100 performs machine learning of the relationship between financial information and asset prices using this financial asset forecast data 200. When performing this machine learning, the machine learning unit 100 may use an accelerator of the image processing unit 11 or the like. As a result, the machine learning unit 100 estimates a dynamics function common to multiple companies and stores it in the model data 210.

[0036] As shown in Figure 3, stock prices deviate from true value (fundamental value) because they are influenced by the herd psychology of investors. The machine learning unit 100 can generate a model that outputs intrinsic value by performing machine learning on financial information and asset prices for multiple companies regardless of the time period. In this case, in order to improve the learning accuracy, the machine learning unit 100 also performs machine learning using the performance forecasts by management or analysts shown in the financial results summary. This enables the machine learning unit 100 to efficiently learn a model that uses observable asset prices as the objective variable, as shown in the examples described below.

[0037] Specifically, the machine learning unit 100 performs machine learning on a model that is a nonlinear extension of the multiple regression type OVM (Olson model) described in Non-Patent Document 1. For this machine learning, it is possible to apply, for example, artificial neural networks with various layer structures, kernel machines, decision trees, Bayesian networks, other Bayesian statistical methods, statistical methods such as regression and multiple regression, and various other artificial intelligence and statistical methods.

[0038] (Step S102) Next, the intrinsic value calculation unit 110 performs an intrinsic value calculation process. The intrinsic value calculation unit 110 reads out the machine-learned model data 210 and inputs the financial information of each company into the calculated dynamics function, thereby calculating the intrinsic value of the asset.

[0039] 3, in this embodiment, the intrinsic value calculation unit 110 inputs the financial information of the company into the calculated dynamics function, thereby removing psychological biases such as noise and outputting only the intrinsic value (true value, fundamental value) of the asset. The intrinsic value calculation unit 110 can regard this intrinsic value of the company as the "theoretical stock price." The intrinsic value calculation unit 110 stores the intrinsic value (theoretical stock price) calculated for each company (stock) in the intrinsic value data 220.

[0040] (Step S103) Next, the value difference calculation unit 120 performs a value difference calculation process. The value difference calculation unit 120 calculates the difference between the intrinsic value calculated by the intrinsic value calculation unit 110 and the asset price as herd psychology.

[0041] According to Figure 3, in this embodiment, the value difference calculation unit 120 can calculate the crowd psychology (psychological bias) itself by calculating the difference between the asset price, which is the current stock price (realized stock price), and the intrinsic value of the asset, which is the calculated theoretical stock price, for each company (stock), i.e., the "deviation" from the intrinsic value.

[0042] In this embodiment, the value difference calculation unit 120 can calculate this herd psychology as PIR (Price Intrinsic-value Ratio), which will be described in detail in the examples below. PIR is a deviation rate similar to PBR (Price Book-value Ratio), and is calculated by regressing the herd psychology of each stock with the average stock price of TOPIX (TOPIX) or the like and calculating the "residual." PIR makes it possible to remove the influence of the entire market and the constant undervaluation and overvaluation specific to each stock. The value difference calculation unit 120 stores the PIR index calculated for each company (issue) in the intrinsic value data 220.

[0043] At this time, the value difference calculation unit 120 can also detect abnormal stock prices based on the calculated crowd psychology. For example, the value difference calculation unit 120 may determine that a stock price is abnormal when the deviation rate in the PIR is outside a specific range from the standard deviation. Alternatively, the value difference calculation unit 120 may detect this when a stock is identified as an "undervalued stock" or an "overvalued stock" as described below. That is, for example, as shown in the following example, the value difference calculation unit 120 may determine that a stock price is abnormal when, among all stocks for which PIRs have been calculated, the stock price is one for which the PIR is selected within the upper or lower 20% range. When such an abnormal stock price is detected, the value difference calculation unit 120 can also warn the user about the stock (company) in question.

[0044] (Step S104) Next, the value difference calculation unit 120 performs a list drawing process. The value difference calculation unit 120 displays a list of crowd psychology as monitoring data 230 based on the period and type of stock. Figure 4 shows an example of this tabulated monitoring data 230. In this example, the vertical axis represents stocks categorized by sector. The horizontal axis represents each period. The graph and open circles in the figure represent examples of ETF purchases by the Bank of Japan.

[0045] In this way, the value difference calculation unit 120 can perform risk prediction management by visualizing crowd psychology. In other words, it is possible to get a comprehensive view of whether each company's stock price is "overvalued" or "undervalued." Specifically, in this example of monitoring data 230, the more companies show synchronized overvaluation and undervaluation, as seen in the striped areas, the more likely it is that a bubble due to changes in the market environment is suspected. The value difference calculation unit 120 can also warn the user about abnormal judgments such as "suspected bubble."

[0046] Specifically, when plotted in the same manner as the example shown in Figure 4, when the price falls from the year-to-date high on February 16 to 27,448 yen on May 13, the black stripes of the abnormality pattern can indicate a "sign" of a fall. The value difference calculation unit 120 can issue a warning of this. In this case, the value difference calculation unit 120 can determine from the correlation between the white circles and the striped patterns in the figure that the Bank of Japan's ETF purchases are stimulating herd psychology, and can also point this out. Although Figure 4 shows the herd mentality in black and white, it is possible to clearly express this herd mentality using colors such as red (overpriced) - blue (underpriced) or green (overpriced) - red (underpriced).

[0047] (Step S105) Next, the asset management unit 130 performs asset management processing. The asset management unit 130 selects stocks for asset management based on the strength of the divergence between the intrinsic value stored in the intrinsic value data 220 and herd psychology, and stores the results in the management data 240. In other words, the asset management unit 130 identifies undervalued stocks and overvalued stocks. Then, the asset management unit 130 refers to the management data 240 and manages the portfolio by going long (buying) on ​​undervalued stocks and short (selling) on ​​overvalued stocks. Specifically, the asset management unit 130 identifies undervalued and overvalued stocks based on the difference between the intrinsic value and the asset price, that is, the strength of herd psychology, which is the divergence between the theoretical stock price and the current stock price.

[0048] More specifically, the asset management unit 130 divides all stocks into quintiles (every 20%) according to the PIR of each company (stock). Then, the asset management unit 130 goes long on the first quintile (undervalued stocks) and short on the fifth quintile (overvalued stocks). This makes it possible to efficiently obtain spread returns, as will be shown in the examples below.

[0049] Thereafter, the value difference calculation unit 120 calculates the theoretical stock price every time new financial information is released. As a result, the asset management unit 130 updates the stocks that make up the portfolio and stores them in the management data 240. In other words, machine learning is retrained and the portfolio is rebalanced every specific period. This completes the stock price evaluation process according to the embodiment of the present invention.

[0050] The above configuration can provide the following effects. Many financial market anomalies that cannot be explained by the EMH (efficient market hypothesis) or CAPM (capital asset pricing model), such as the value stock effect and the small-cap effect, have been reported in the past, and the risk premium hypothesis and mispricing hypothesis are representative of the mechanisms by which these anomalies arise. Of these, the mispricing hypothesis is supported by behavioral economics and recognizes the possibility that the price of a financial asset may diverge from its intrinsic value. This divergence (mispricing) occurs due to the psychological biases of investors. Because modeling human psychology is difficult, fundamental analysis models intrinsic value. Representative deductive models include the dividend discount model (DDM) and the residual income model (RIM), but because both include growth forecasts related to corporate finances, intrinsic value cannot be uniquely determined. Therefore, it is possible to consider inductive modeling from data. For example, the OVM model described in Non-Patent Document 1 exists, but it makes numerous assumptions and the intrinsic value, which is the objective variable, is unobservable.

[0051] In contrast, the stock price evaluation device 1 according to an embodiment of the present invention is characterized by comprising a machine learning unit 100 that performs machine learning on the relationship between the financial information of multiple companies over multiple periods and asset prices, and estimates a dynamics function common to the multiple companies; an intrinsic value calculation unit 110 that calculates the intrinsic value of the asset using the dynamics function estimated by the machine learning unit 100; and a value difference calculation unit 120 that calculates the difference between the intrinsic value calculated by the intrinsic value calculation unit 110 and the asset price as crowd psychology.

[0052] This configuration allows us to calculate the intrinsic asset value based on the difference between the current stock price, which indicates the company's value, and the asset price, and evaluate the difference from the asset price. In other words, machine learning can extract herd psychology, which is mispricing caused by the psychology of collective investors. This allows us to evaluate theoretical stock prices with higher accuracy.

[0053] Furthermore, as global interest rates remain low for a prolonged period, investing in risky assets has become as important as lending for regional financial institutions, primarily banks. On the other hand, the Financial Services Agency is calling on financial institutions to improve their risk management, for example by carefully selecting the risks they should take, monitoring the amount of risk, and controlling the amount of risk. In contrast, the stock price evaluation device 1 according to this embodiment can efficiently use machine learning to enhance risk management. This makes it possible to improve the efficiency of risk management and portfolio management by using it in combination with the specialized knowledge of experienced people.

[0054] Furthermore, in the stock price evaluation device 1 according to the embodiment of the present invention, the machine learning unit 100 can use, in machine learning, performance forecasts by management or analysts indicated in the financial results summary. This configuration allows for the use of expert knowledge and tacit knowledge from the parties involved in addition to objective observations of financial information. In other words, it creates room for not only data-driven, objective AI estimation but also subjective human expert knowledge. This is expected to have the effect of flexibly expanding the framework of machine learning, which tends to be rigid.

[0055] In recent years, asset management has become no exception, with the increasing use of AI technology and machine learning. However, these AI and machine learning technologies have presented the so-called "black box" problem, where the results are difficult to interpret. In this regard, the conventional OVM model described in Non-Patent Document 1 places importance on interpretability, but includes many constraints such as the assumption of linearity, etc. For this reason, it has not been possible to accurately calculate the original theoretical stock price.

[0056] In contrast to this, in the stock price evaluation device 1 according to the embodiment of the present invention, the dynamics function is characterized by being an extension of the OVM model (Ohlson Valuation Model) to a nonlinear model. By configuring it in this way, the OVM model, which is a corporate valuation model based on corporate financial information, can be extended with machine learning. This reduces the shortcomings of conventional corporate valuation models and enables calculation of intrinsic value with higher accuracy. In other words, compared to conventional theoretical stock price models, by adding nonlinearity through machine learning, the versatility of the model is improved, and more realistic theoretical stock prices can be calculated. Furthermore, the dynamics function according to this embodiment is less of a black box like "AI management" that utilizes so-called alternative data. This makes it easier to explain and more transparent, making it more acceptable to users like undervalued stock investments, and even enabling the creation of publicly offered funds.

[0057] In contrast to this, in the stock price evaluation device 1 according to this embodiment, the value difference calculation unit 120 is characterized in that it detects abnormal stock prices based on crowd psychology. With this configuration, it is possible to constantly monitor the deviation from the current stock price, thereby making it possible to evaluate the risk of the entire stock market. In other words, the stock price evaluation device 1 according to this embodiment makes it possible to continuously monitor a huge number of investment stocks in real time at high speed, in large quantities, automatically, objectively, and stably. This makes it possible to notify users of abnormal stock prices and obtain buy / sell instructions.

[0058] Furthermore, in the stock price evaluation device 1 according to the embodiment of the present invention, the value difference calculation unit 120 is characterized in that it draws a list of crowd psychology based on the period and the type of stock. This configuration makes it possible to use it to determine investment positions in asset management. In other words, it acts as a "protective gear" or "umbrella" for asset management, helping to assess market conditions and make buying and selling decisions. Specifically, as shown in the example of monitoring data 230 in Figure 4, it makes it possible to observe the market environment objectively and in real time, like a "nowcast" on a weather radar.

[0059] Furthermore, the stock price evaluation device 1 according to the embodiment of the present invention is characterized by further comprising an asset management unit 130 that identifies undervalued stocks and overvalued stocks based on the herd psychology calculated by the value difference calculation unit 120. By configuring it in this way, it can be used to judge whether a stock is undervalued or overvalued, just like PBR (price-to-book ratio) or V / P ratio (value-to-price ratio). This makes it possible to build a portfolio in a direction that corrects mispricing (herd psychology) and observe subsequent investment performance. It also makes it possible to deliver undervalued and overvalued stocks via financial information distribution vendors.

[0060] In addition, in recent years, empirical analysis has shown that the value stock effect has disappeared, pointing out the ineffectiveness of this type of investment style. This is because, although identifying value stocks relied on corporate valuation models, it was difficult to calculate true corporate value using conventional models.

[0061] In contrast to this, in the stock price evaluation device 1 according to the embodiment of the present invention, the asset management unit 130 is characterized by managing a portfolio by going long on undervalued stocks and short on overvalued stocks.

[0062] By configuring it in this way, it is possible to significantly improve the "return / risk ratio" compared to the past. In other words, considering the efficiency of financial markets, the greater the deviation, the more likely it is that a correction to the fair price will occur, and by managing a portfolio using this correction process, it is possible to obtain good investment performance, as will be shown in the examples below. Specifically, by utilizing the corporate valuation model according to this embodiment, which is more accurate than conventional models, in portfolio management, it is possible to confirm profitability that exceeds the risk premium through statistical testing. As a result, although the financial industry has pointed out a slump in "undervalued stock investment" in recent years, the operation according to this embodiment can demonstrate its effectiveness.

[0063] Other Embodiments In the above embodiment, an example in which a PC or the like is used alone as the stock price evaluation device 1 has been described. However, the stock price evaluation device 1 may be configured as a server-client type system using a plurality of servers, general-purpose computers, etc., which are accessed from terminals such as PCs and smartphones.

[0064] Furthermore, information such as theoretical stock prices, undervalued stocks, and overvalued stocks calculated by the stock price evaluation device 1 according to this embodiment can be distributed by a financial information distribution vendor to terminals such as PCs and smartphones in addition to financial information. Here, the stock price evaluation device 1 is not limited to Japanese stocks, and can be applied to global stocks including U.S. stocks. This configuration makes it possible to accommodate a variety of configurations.

[0065] Furthermore, in the above-described embodiment, the OVM model is used as the original model and is nonlinearly extended, but other types of enterprise valuation models may also be used. Furthermore, it is possible to introduce dummy variables for industries or specific companies into the model, and to change the frequency of machine learning retraining and portfolio rebalancing to monthly, quarterly, semi-annually, annually, etc.

[0066] In the above embodiment, an example has been described in which the current stock price is calculated as the asset price and the theoretical stock price is calculated as the asset value. However, the stock price evaluation device according to the present invention can be similarly applied to the evaluation, monitoring, and management of bonds, FX (Foreign Exchange, foreign exchange margin trading), commodity investments (commodity futures trading), and other assets in addition to stock prices. By configuring it in this way, it is possible to conduct transactions based on the discrepancy between asset prices and intrinsic value, and it is expected that assets will increase. [Example]

[0067] Next, the present invention will be described in more detail based on examples, but the following specific examples are not intended to limit the present invention.

[0068] (Corporate valuation model) Stock Price P t The intrinsic value of V t Dividend per share is d t The rate of return (cost of capital) expected by investors is calculated using the following formula (1):

[0069]

number

[0070] where E t indicates the net income for the period t. Assuming that there is no mispricing due to the efficiency of financial markets, P t =V t Therefore, the DDM (Dividend Discount Model) is obtained by the following equation (2).

[0071]

number

[0072] Furthermore, net assets per share is B t , net income per share x t , residual profit x a t =x t -rB t-1 The clean surplus relationship (Bt =B t-1 +x t -d t ), the RIM (residual profit model) is obtained as shown in the following equation (3).

[0073]

number

[0074] Since this model involves predictions for an infinite future, some assumptions about the dynamics of time evolution are required. a t The time evolution of the LIM (Linear Information Model) is assumed as follows:

[0075]

number

[0076]

number

[0077] From equation (4), ν t =E t [x a t+1 ]-ωx a t By substituting these into the RIM in equation (3) and rearranging, we obtain the OVM (Ohlson model) in equation (6) below.

[0078]

number

[0079] Here, the coefficients of the OVM are expressed by the following equations (7) to (10).

[0080]

number

[0081] These are estimated using LIM or CAPM, and then ω, γ, and r are substituted into the above equations (7) to (10) to obtain the estimated intrinsic value ^V t (Here, the "^" next to the alphabetical character is a hat shown above the alphabetical character, and the same notation will be used hereafter.) Or, obtain the observable P t The partial regression coefficients are estimated using the following equation (11), which is a multiple regression equation for

[0082]

number

[0083] Then, V t The estimated value of ^V t get.

[0084]

number

[0085] Additionally, ^V t and P t By examining the deviation of asset price P t It is possible to determine whether a stock is cheap or expensive. In order to adjust for differences in scale due to company size, we use the last month's stock price P t-1 You can divide it by B t The PBR (Price Book-value Ratio) divided by the PBR may be used as the objective variable. In this case, the following equation (13) is obtained.

[0086]

number

[0087] In either case, E t [x t+1For [ ], it is preferable to use stock analyst forecasts (analyst forecasts). For example, in Japan, forecasts made by management themselves are published in quarterly financial results briefs. This is available to anyone and is useful information that is not subordinate to analyst forecasts, so in this embodiment, it is preferable to use management forecasts.

[0088] (Nonlinear modeling of OVM using machine learning) The corporate valuation model in the above-mentioned embodiment makes simple assumptions for theoretical derivation, prioritizing deductive interpretation over correspondence with more complex reality. However, since financial data is generally non-stationary, it is difficult to estimate the coefficients of LIM in equations (4) and (5). First of all, the time evolution dynamics of residual profits is not linear like LIM, and is likely to have non-linearity. This is because if residual profits are positive, the business expands, and if negative, the business contracts, so the persistence coefficient ω is not a constant but a function f(x a t ) is considered to be the case.

[0089] In this embodiment, priority is given to correspondence with reality, and OVM is expanded by introducing machine learning. However, since the financial information used for corporate valuation changes only a few times a year, it is difficult to secure a sufficient amount of data for machine learning. Also, although the corporate valuation model assumes that each coefficient is constant, in reality, there is a possibility that it may change over time. Therefore, in this example, the use of old data is reduced.

[0090] Therefore, it is preferable to increase the number of data by using panel data that includes not only the time series direction but also the cross-sectional direction. t ]=P t -E[ε t ] is P t This improves the validity of the coefficient estimates in equation (11). Here, the model coefficient θ is considered to differ for each individual company i. In particular, the cost of capital r may be estimated using the capital asset pricing model (CAPM) shown in the following equation (14). Note that when considering risk premiums other than market risk, a multi-factor model including more risk factors may be used.

[0091]

number

[0092] where r f is the risk-free interest rate, E t [r m,t+1 ] is the expected market return, β i,t is the market beta of company i. This market beta is a value indicating sensitivity to market risk factors. In other words, even with conventional OVM, the partial regression coefficient θ (Equation (7) to Equation (10)) involving r differs for each company i, so coefficient estimation by cross-sectional regression is not possible. Therefore, in this embodiment, characteristics unique to company i are used as explanatory variables, and F, the dynamics common to all companies, is estimated by cross-sectional machine learning. Therefore, equation (13) may be replaced with the following equation (15).

[0093]

number

[0094] This F is estimated using machine learning such as a decision tree, as described below. This estimated value of F is hereinafter referred to as "^F" (dynamics function). Using this ^F estimated by machine learning, the value of the following equation (16) is calculated.

[0095]

number

[0096] where t means monthly and x i,qtis the net income at the end of the previous quarter (actual value per share), d i,yt is the dividend at the end of the previous fiscal year (actual value per share), E t [x i,qt+1 ] is the management's estimated net income per share at the end of the current quarter, E t [d i,yt+1 ] is the expected dividend (management forecast per share) for the end of this fiscal year. Furthermore, the capital cost r i,t As a variable related to i,t and volatility σ i,t is calculated from the monthly returns of company i for the most recent 36 months, and the market expected return is E t [r m,t+1 ] is the average monthly return of TOPIX for the last 36 months. Note that there is a time lag of up to two months before financial information after settlement is made public, and it takes time for this to be incorporated into stock prices. Therefore, the stock price P i,t uses the value realized three months later. i,t , σ i,t , E t [r m,t+1 ] has no time lag, so P i,t The values ​​for the same month were used.

[0097] For machine learning, XGBoost decision tree was used, the number of decision trees was 1000, the learning rate was 0.03, the loss function was RMSE, and other hyperparameters were set to default values. i,t Since F fluctuates every month, the most recent 36 months (excluding the current month) were used as the learning period, and F was re-learned every month. Financial information from three months prior was input into the estimated F, and the corporate value^V i,t was estimated. The above method was tested. The analysis period was from January 31, 2008 to June 30, 2021. The target companies were selected based on the following criteria:

[0098] -The company is listed on the First Section of the Tokyo Stock Exchange. - General business companies (excluding banks, securities, insurance, and other financial services). ·Net worth is always positive. ·The quarterly or annual financial data does not show losses for two or more consecutive periods.

[0099] Among these, when the financial data shows a loss for only one period, it was supplemented with the previous value. The financial data and stock price data were obtained from Refinitiv Eikon (<URL="https: / / www.refinitiv.com / ").

[0100] (Result) Figure 5 shows the estimated intrinsic value ^V i,t and the asset price P i,t correlation diagram. Generally, it fits on a straight line, and the deviation part is considered to be mispricing due to investor psychology. Therefore, the deviation rate ξ i,t was calculated by the following formula (17).

[0101]

Number

[0102] This result is shown in Figure 6. Investor psychology (psychological bias) oscillates around 0, and a steady mean reversion was confirmed. However, due to industry types and the popularity of the company itself, the market price P i,t may constantly deviate from the intrinsic value. In this embodiment, the constant deviation is corrected by subtracting the moving average value for each company i. This calculation formula is shown in the following formula (18). It is also possible to improve by devising machine learning through the application of dummy variables.

[0103]

Number

[0104] Here, the deviation rate after this correction is ξ † i,t Let it be. In this embodiment, M = 36 (for 36 months), and overvalued and undervalued stocks were discriminated based on ξ † i,t Based on the similarity with PBR, in this embodiment, ξ †i,t is called the PIR (Price Intrinsic-value Ratio) indicator. This corrected ξ † i,t The average value is almost the same as in Figure 6, but the standard deviation has decreased. i,t <0) or overvalued stocks (ξ i,t >0) could be corrected.

[0105] Figure 8 shows the feature importance of explanatory variables. i,yt+1 ]) is particularly important. On the other hand, the expected net income (Realized net income) Et[x i,qt+1 ] is less important, but this is thought to be due to the overlap of information with the expected dividend. i,qt , d i,yt ) is highly important, and finally, the volatility of the cost of capital (Sigma of return rates) (σ i,t ), Market beta of CAPM (β i,t ), market expected return (Expected net income) E t [r m,t+1 ] followed.

[0106] (Verification of validity through portfolio management) Asset prices P do not necessarily reflect intrinsic value V, and temporary mispricing may occur. As shown in Figure 6, when this occurs, the asset price is expected to move in a way that corrects it to intrinsic value due to the efficiency of financial markets. For this reason, we verified the validity of the PIR indicator shown in equation (18) above through portfolio management that utilizes this correction process. The portfolio management methodology is as follows:

[0107] Machine learning retraining and PIR calculations are performed at the end of each month. Divide investment target stocks into quintiles based on PIR. · Short the 1st quintile (overvalued stocks) and long the 5th quintile (undervalued stocks). All buying and selling ratios will be equal weighted. ·Rebuild your portfolio every month by repeating the above at the end of the following month.

[0108] Figure 9 shows the return r obtained by a portfolio of only long (purchasing) positions (long portfolio) or a portfolio of only short (short selling) positions (short portfolio). p,t The graph below shows the cumulative return (cumulative return). In Figure 9, the straight line represents the cumulative value of the 0.5% monthly management fee. As a result, the long portfolio outperformed the benchmark TOPIX, and it can be said that the value (undervalued) stock effect was extracted. On the other hand, the short portfolio, which allows for the sale of growth stocks, tends to be more susceptible to the trends of the times.

[0109] Figure 10 shows the cumulative active return of the long portfolio for each quantile. In Figure 10, a long portfolio was constructed for each quantile from the 5th quartile (lowest 20%, 5th quartile) to the 1st quartile (highest valuation, 1st quartile), and the active return (r p,t -r m,t ) are accumulated. Profitability is ranked in quantile order, confirming the validity of stock evaluations using the PIR index.

[0110] Figure 11 shows the cumulative returns of a long-short portfolio, where the top 20% (1st quantile) is short and the bottom 20% (5th quantile) is long, as a graph of the PIR index in equation (18). "PIR of Eq. (18)" in FIG. 11 is a graph of the cumulative return of this example. As a comparative example, a long-short portfolio based on the conventional PBR index is shown in the following equation (19). This is "PBR of Eq. (19)" in Figure 11.

[0111]

number

[0112] Furthermore, as a comparative example, the following equation (20) shows an example in which the average value for M=36 (36 months) is removed to correct for persistent mispricing, similar to equation (18). This is the "PBR of Eq. (20)" in Figure 11.

[0113]

number

[0114] where η i,t is the PBR index, and η † i,t is the corrected value. As a result, the PIR index in this example achieved a consistently higher return than the PBR index and TOPIX, and the risk-return ratio (mean / std) was also significantly improved. In other words, it is believed that the PIR index was able to extract market mispricing as expected.

[0115] Next, to verify whether the mispricing extracted by the PIR index contains an anomaly that cannot be explained by the risk premium, we calculated the return r p,t was subjected to regression analysis using control variables as shown in equation (21) below.

[0116]

number

[0117] Here, here r f,t is the risk-free interest rate, f Mkt-RF t is the market factor return minus the risk-free interest rate, f SMB t is the size factor return, f HML tare the value factor returns, which were obtained from the KRFrench homepage (URL=”https: / / mba.tuck.dartmouth.edu / pages / faculty / ken.french / data_library.html (last accessed: October 1, 2021)”). The test results of the coefficients are shown in Table 1 below.

[0118] [Table 1]

[0119] A significance test was performed using a three-factor model in Table 1. The "*" and "**" next to the coefficients indicate p<0.05 and p<0.001, respectively.

[0120] As a result, we were able to confirm strong significance, particularly in the α of the long-short portfolio, and the existence of an anomaly that cannot be explained by the risk premium in equation (21). Naturally, there remains the possibility that premiums due to risk factors other than equation (21) may be included, but it is highly likely that we were able to extract mispricing due to investor psychology.

[0121] (summary) By extending the Ohlson model in Non-Patent Document 1 using machine learning, we were able to evaluate the discrepancy between market price and intrinsic value. Furthermore, we confirmed that the returns obtained through portfolio management can be expressed in terms of alpha other than risk factors, and showed that this discrepancy may be a market mispricing.

[0122] Furthermore, it goes without saying that the configurations and operations of the above-described embodiments are merely examples, and can be modified as appropriate within the scope of the present invention. [Explanation of symbols]

[0123] 1 Stock Price Valuation Device 10 Control Unit 11 Image processing section 12 Storage section 13 Input section 14 Display section 15 Transmitter / Receiver 100 Machine Learning Department 110 Intrinsic Value Calculation Department 120 Value difference calculation unit 130 Asset Management Department 200 Financial Assets Projection Data 210 model data 220 Intrinsic Value Data 230 Monitoring Data 240 Operational Data 300 Stock Valuation Program 310 Stock Price Monitoring Program 320 Asset Management Program

Claims

1. a machine learning unit that performs machine learning on the relationship between financial information of a plurality of companies over a plurality of periods and asset prices, and estimates a dynamics function common to the plurality of companies; an intrinsic value calculation unit that calculates the intrinsic value of an asset using the dynamics function estimated by the machine learning unit; a value difference calculation unit that calculates the difference between the intrinsic value calculated by the intrinsic value calculation unit and the asset price as a herd psychology; The value difference calculation unit draws a list of the crowd psychology based on the period and the type of issue. A stock price evaluation device characterized by:

2. The machine learning unit also uses the performance forecast by the management or the performance forecast by the analyst, which is indicated in the financial results summary, in the machine learning.

2. The stock price evaluation device according to claim 1.

3. The dynamics function is an extension of the OVM model (Ohlson Valuation Model) to a nonlinear model.

3. The stock price evaluation device according to claim 1 or 2.

4. The value difference calculation unit detects abnormal stock prices based on the crowd psychology.

4. The stock price evaluation device according to claim 1, wherein:

5. The asset management unit further includes an asset management unit that identifies undervalued stocks and overvalued stocks based on the herd psychology calculated by the value difference calculation unit.

5. The stock price evaluation device according to claim 1.

6. The asset management department Manage your portfolio by going long on the undervalued stocks and short on the overvalued stocks.

6. The stock price evaluation device according to claim 5.

7. A stock price evaluation program executed by a stock price evaluation device, Machine learning is performed on the relationship between financial information and asset prices of multiple companies over multiple periods, and a dynamics function common to the multiple companies is estimated; The estimated dynamics function is used to calculate the intrinsic value of the asset. Calculating the difference between the calculated intrinsic value and the asset price as herd psychology; The herd psychology is displayed based on the period and type of stock. A stock price evaluation program characterized by:

8. Identifying undervalued stocks and overvalued stocks based on the herd psychology calculated by the stock price evaluation program according to claim 7; Manage the portfolio by going long on the identified undervalued stocks and short on the identified overvalued stocks. An asset management program characterized by:

9. A stock price evaluation method executed by a stock price evaluation device, the stock price evaluation device Machine learning is performed on the relationship between financial information and asset prices of multiple companies over multiple periods, and a dynamics function common to the multiple companies is estimated; The estimated dynamics function is used to calculate the intrinsic value of the asset. Calculating the difference between the calculated intrinsic value and the asset price as herd psychology; Illustrate the herd psychology based on time period and type of stock. A stock price valuation method characterized by:

10. Abnormal stock prices are monitored based on the crowd psychology calculated by the stock price evaluation method according to claim 9. A stock price monitoring method characterized by:

11. Identifying undervalued stocks and overvalued stocks based on the herd psychology calculated by the stock price evaluation method according to claim 9; Manage the portfolio by going long on the identified undervalued stocks and short on the identified overvalued stocks. An asset management method characterized by:

Images