Stock price prediction system and stock price prediction program

Abstract

We provide a stock price prediction system and program that accurately grasps trends in stock price fluctuations. [Solution] The stock price prediction system 10 includes a reference value setting unit 11 that obtains the closing stock price on a reference date for a company to be predicted and sets the stock price as a reference value; a stock price acquisition unit 12 that obtains the daily closing stock prices of the company over a predetermined period as daily stock prices and stores them in a record DB 16; a fluctuation rate calculation unit 13 that calculates the fluctuation rate between the reference value and the daily stock prices stored in the record DB and records it in a storage DB 17 as a daily fluctuation rate; and a trend analysis unit 14 that analyzes the trend of the company's stock price based on the daily fluctuation rate recorded in the storage DB. The trend analysis unit uses the daily fluctuation rate recorded in the storage DB to perform an enthalpy transformation as a linear function of the daily fluctuation rate value on a day arbitrarily selected within a predetermined period and the daily fluctuation rate value on the current day, thereby showing the trend of the company's stock price as a line.

Description

Technical Field

[0001] The present invention relates to the technology of a stock price prediction system and a stock price prediction program for predicting the stock price of a company.

Background Art

[0002] Conventionally, stock price prediction apparatuses that predict daily fluctuating stock prices have been known. For example, Patent Document 1 discloses a "time-series data prediction method" characterized in that identification and prediction of highly non-linear time-series data are performed by solving a non-linear differential equation representing a main variable and an auxiliary variable, and identifying the main variable to perform prediction.

[0003] It is stated that the "time-series data prediction method" disclosed in Patent Document 1 is particularly useful for predicting highly non-linear time-series data, especially time-series data in securities such as stock prices and exchange rates, the financial field, and the distribution field such as consumer goods demand.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] An object of the present invention is to provide a stock price prediction system that grasps the tendency of stock price fluctuation with high accuracy by analyzing the rate of change from a stock price reference value in time series.

Means for Solving the Problems

[0006] In order to achieve the above object, the stock price prediction system according to a first aspect of the present invention includes: A stock price prediction system for predicting the stock price of a company, comprising: A reference value setting unit obtains the closing stock price on the reference date for the company to be predicted and sets that stock price as the reference value, A stock price acquisition unit acquires the daily closing stock prices of the aforementioned company over a predetermined period as daily stock prices and stores them in a record DB, A fluctuation rate calculation unit calculates the rate of change between the aforementioned reference value and the daily stock price stored in the record DB, and records it in the storage DB as the daily fluctuation rate. A trend analysis unit analyzes the trend of the stock price of the company during the period to be predicted, based on the daily fluctuation rate recorded in the storage DB. Equipped with, The trend analysis unit uses the daily rate of change recorded in the storage DB to perform an enthalpy transformation as a linear function of the daily rate of change on a day arbitrarily selected within the predetermined period and the daily rate of change on the current day, thereby showing the trend of the company's stock price as a line. It is characterized by the following:

[0007] The stock price prediction program according to the second invention is: A program that predicts the stock price of a company, which is controlled by a computer. A base value setting step involves obtaining the closing stock price on the base date for the company to be predicted and setting that stock price as the base value, A stock price acquisition step involves acquiring the daily closing stock prices of the company for a predetermined period as daily stock prices and saving them in a record DB, A fluctuation rate calculation step which involves calculating the rate of change between the aforementioned reference value and the daily stock price stored in the record DB, and recording it in the storage DB as the daily fluctuation rate, A trend analysis step that analyzes the trend of the stock price of the company during the period to be predicted, based on the daily rate of change recorded in the storage DB, In order to execute, The trend analysis step involves using the daily rate of change recorded in the storage DB to perform an enthalpy transformation as a linear function of the daily rate of change on a day arbitrarily selected within the predetermined period and the daily rate of change on the current day, thereby showing the trend of the company's stock price as a line. It is characterized by the following:

[0008] The stock price prediction system according to the third invention is: A stock price prediction system that predicts the stock price of a company, A stock price acquisition unit acquires the daily closing stock prices for a specified period for the companies to be predicted and stores them in a record database. A trend analysis unit analyzes the trend of the stock price of the company during the period to be predicted, based on the daily stock price recorded in the aforementioned record DB. Equipped with, The trend analysis unit uses the daily stock prices recorded in the record DB to perform an enthalpy transformation as a linear function of the daily stock price value on a day arbitrarily selected within the predetermined period and the daily stock price value on the current day, thereby showing the trend of the company's stock price as a line. It is characterized by the following:

[0009] The stock price prediction program according to the fourth invention is: A program that predicts the stock price of a company, which is controlled by a computer. A stock price acquisition step involves obtaining the daily closing stock prices of the companies to be predicted for a predetermined period and saving them in a record database. A trend analysis step that analyzes the trend of the stock price of the company during the period to be predicted, based on the daily stock price recorded in the aforementioned record DB, In order to execute, The trend analysis step involves using the daily stock prices recorded in the record DB to perform an enthalpy transformation as a linear function of the daily stock price values ​​on arbitrarily selected days within the predetermined period and the daily stock price values ​​on the current day, thereby showing the trend of the company's stock price as a line. It is characterized by the following: [Effects of the Invention]

[0010] According to the present invention, by time-series analysis of the rate of change from a stock price reference value for the price of a company whose price fluctuates in a trading market, it becomes possible to grasp the trend of stock price fluctuation with high accuracy, and further, it can be expected to improve prediction accuracy for future trends. [BRIEF DESCRIPTION OF THE DRAWINGS]

[0011] [Figure 1] FIG. 1 is a functional configuration diagram showing the functional configuration of a stock price prediction system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart showing the overall processing procedure in the stock price prediction system according to an embodiment of the present invention. [Figure 3] FIG. 3 is a schematic diagram showing an example of enthalpy conversion in the stock price prediction system according to an embodiment of the present invention. [MODE FOR CARRYING OUT THE INVENTION]

[0012] Hereinafter, modes for carrying out the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiments described below.

[0013] FIG. 1 is a functional configuration diagram showing the functional configuration of the stock price prediction system according to an embodiment of the present invention. As shown in FIG. 1, the stock price prediction system 10 includes a reference value setting unit 11, a stock price acquisition unit 12, a change rate calculation unit 13, and a trend analysis unit 14, and is configured to analyze the trend of the company's stock price and calculate a prediction trend by analyzing the rate of change from a stock price reference value for a company to be predicted in time series.

[0014] Here, the stock price prediction system 10 is a general-purpose computer device, for example, equipped with a processing unit (CPU), main memory (RAM), auxiliary storage devices such as HDDs, SSDs, and flash memory, input devices such as keyboards, mice, and touch panels, output devices such as displays and speakers, and communication devices for communicating with external devices. Alternatively, a smartphone, tablet, or PC (Personal Computer) can be used as the computer device.

[0015] The reference value setting unit 11 obtains the closing stock price of the company to be predicted on the reference date and sets the stock price as the reference value.

[0016] Here, the "companies to be included in the prediction" can be configured to have information on one or more companies (for example, Company A and Company B) pre-set. Alternatively, the system can be configured so that information on one or more companies (for example, Company A and Company B) is input and set from an input device in a timely manner according to the operator's instructions.

[0017] Furthermore, the above-mentioned "reference date" can be configured to have pre-set information about a past date to be used as the basis for the analysis. Alternatively, it may be configured so that the information about the past date to be used as the reference is input and set from an input device in a timely manner according to the operator's instructions.

[0018] Furthermore, as a means of obtaining the closing stock price of the aforementioned company on the "reference date" mentioned above, the system can be configured to obtain the target stock price information by, for example, coordinating with other systems via a communication network. Alternatively, the system may be configured so that the target stock price information is input and set from an input device according to the operator's instructions.

[0019] The stock price acquisition unit 12 acquires the daily closing stock prices for a predetermined period for the companies set in the reference value setting unit 11, and stores them as daily stock prices in the record DB 16. In other words, the record DB 16 stores daily stock prices for each company that is the target of the prediction.

[0020] Here, the "predetermined period" can be configured so that the date information of the past period to be analyzed is set in advance. Alternatively, it may be configured so that the date information of the past period to be analyzed is input and set from the input device in a timely manner according to the operator's instructions.

[0021] Furthermore, as a means of obtaining the daily closing stock prices for the "specified period" mentioned above, the system can be configured to obtain the target stock price information by, for example, coordinating with other systems via a communication network. Alternatively, the system may be configured to input and obtain the target stock price information from an input device based on instructions from an operator.

[0022] The fluctuation rate calculation unit 13 calculates the fluctuation rate between the reference value and the daily stock price (the closing stock price for each day over a predetermined period) stored in the record DB 16 for the target company, and records it as the daily fluctuation rate in the storage DB 17. In other words, the storage DB 17 will contain the daily fluctuation rate for each target company as time-series data.

[0023] Furthermore, the fluctuation rate calculation unit 13 can be configured to set multiple comparison dates within the period from 50 days prior to the current day, calculate the fluctuation rate between the reference value and the daily stock price on the comparison date stored in the record DB 16, and record it as the daily fluctuation rate in the storage DB 17. In other words, when calculating the daily fluctuation rate, it can be configured to use the daily stock prices on multiple comparison dates within the predetermined period, rather than using all the daily stock prices for the predetermined period.

[0024] The trend analysis unit 14 analyzes the trend of the company's stock price during the period to be predicted, based on the daily fluctuation rate recorded in the storage DB 17.

[0025] Here, the "period to be predicted" can be configured so that information about the period to be predicted is set in advance. Alternatively, the system may be configured so that information about the period to be predicted is input and set from an input device in a timely manner according to the operator's instructions.

[0026] Furthermore, when analyzing the stock price trend of the company, the trend analysis unit 14 can be configured to show the stock price trend of the company as a line by using the daily fluctuation rate recorded in the storage DB 17 and performing an enthalpy transformation as a linear function of the daily fluctuation rate value on a day arbitrarily selected within the predetermined period and the daily fluctuation rate value on the current day.

[0027] In addition to the configuration described above, the trend analysis unit 14 may be configured to analyze the trend of the company's stock price during the period to be predicted, based on the daily stock price recorded in the record DB 16. In this case, when analyzing the trend of the company's stock price, the trend analysis unit 14 can be configured to show the trend of the company's stock price as a line by performing an enthalpy transformation as a linear function of the daily stock price value on a day arbitrarily selected within the predetermined period and the daily stock price value on the current day, using the daily stock price recorded in the record DB 16.

[0028] Next, the process executed by this system will be explained using the flowchart shown in Figure 2. Figure 2 is a flowchart showing the overall processing procedure in a stock price prediction system according to an embodiment of the present invention.

[0029] <Step S11> For the companies to be predicted, the closing stock price of the said company on the reference date is obtained and set as the reference value.

[0030] <Step S12> For the companies to be predicted, the daily closing stock prices for a specified period are obtained as daily stock prices and stored in the record DB16. In other words, the record DB16 stores daily stock prices for each company that is being predicted.

[0031] <Step S13> For the companies to be predicted, the rate of change between the baseline value set in step S11 and the daily stock price (the closing stock price for each day over a predetermined period) stored in the record DB16 is calculated and recorded in the storage DB17 as the daily rate of change. In other words, the storage DB17 records the daily rate of change for each company to be predicted as time-series data.

[0032] Furthermore, when calculating the daily rate of change, instead of using all daily stock prices for a predetermined period, it is also possible to use daily stock prices for multiple comparison dates within a predetermined period. That is, when calculating the daily rate of change, multiple comparison dates can be set within the period from 50 days ago to the present day, and the rate of change between the reference value and the daily stock price for the comparison date stored in the record DB16 can be calculated and recorded as the daily rate of change in the storage DB17.

[0033] <Step S14> Based on the daily fluctuation rate recorded in the storage DB17, the trend of the company's stock price during the period to be predicted is analyzed and a predicted value is calculated. Specifically, when analyzing the trend of the company's stock price, the daily fluctuation rate recorded in the storage DB17 is used to perform an enthalpy transformation as a linear function of the daily fluctuation rate value on an arbitrarily selected day within the predetermined period and the daily fluctuation rate value on the current day, thereby representing the trend of the company's stock price as a line.

[0034] Next, we will explain the procedure for calculating predicted values ​​using enthalpy transformation. As shown in Figure 3, from the values ​​of the rate of change or stock price, a line is drawn using the current day's value and the previous day's value, and arbitrarily selected past values ​​(for example, 5 days ago, 10 days ago, 25 days ago, 50 days ago) are moved onto the vertical line of the previous day's value. The future trend is predicted by the angle of the line drawn between the moved points and the current day's value, and whether the line is rising or falling. The tangent line y is derived from the equation y = ax + b. For example, if the lines with past values ​​all show an upward trend and the angle is acute, and the line drawn using the current day's value and the previous day's value shows an obtuse downward trend, this is information to judge as a sell signal. Also, if the lines with past values ​​all show a downward trend and the angle is acute, and the line drawn using the current day's value and the previous day's value shows an obtuse upward trend, this is information to judge as a buy signal.

[0035] Furthermore, for volatility or stock prices, multiple comparison dates are set at arbitrary points (e.g., 50 days ago, 25 days ago, 10 days ago, 5 days ago). The previous day's value is used as the baseline, and the current day's value and arbitrarily selected past values ​​(e.g., 5 days ago, 10 days ago, 25 days ago, 50 days ago) are moved onto a vertical line representing the previous day's value. The moved points are then compared with the current day's value, and the trend from the past to the present is shown by a line representing this trend. This enthalpy transformation provides information that predicts future trends.

[0036] By performing the above data processing procedure (steps S11 to S14), it becomes possible to analyze the rate of change from the stock price baseline for the target company in a time series, and to grasp the trend of stock price fluctuations with high accuracy.

[0037] The above data processing procedure (steps S11 to S14) may also be implemented as a method executed by a computer, or as a program to be executed by a computer.

[0038] Furthermore, in the above data processing procedure (steps S11 to S14), stock prices may be used instead of the rate of change. That is, the trend of stock prices is used instead of the trend of the rate of change. Since the amount of change is not amplified compared to the rate of change, the angle of the line drawn by the enthalpy transformation becomes obtuse, but it can still be used as a prediction method.

[0039] As described above, the stock price prediction system of the present invention analyzes the price of a company whose price fluctuates in the trading market using the daily rate of change from the stock price reference value (or daily stock price) by enthalpy conversion, making it possible to grasp the trend of stock price fluctuations with high accuracy, and it is expected that the accuracy of future trends will be further improved. [Explanation of Symbols]

[0040] 11...Reference value setting section 12…Stock Acquisition Section 13...Variability calculation unit 14…Trend analysis department 16…Record DB 17…Storage DB

Claims

1. A stock price prediction system that predicts the stock price of a company, A reference value setting unit obtains the closing stock price on the reference date for the company to be predicted and sets that stock price as the reference value, A stock price acquisition unit acquires the daily closing stock prices of the aforementioned company over a predetermined period as daily stock prices and stores them in a record DB, A fluctuation rate calculation unit calculates the rate of change between the aforementioned reference value and the daily stock price stored in the record DB, and records it in the storage DB as the daily fluctuation rate. A trend analysis unit analyzes the trend of the stock price of the company during the period to be predicted, based on the daily fluctuation rate recorded in the storage DB. Equipped with, The trend analysis unit uses the daily rate of change recorded in the storage DB to perform an enthalpy transformation as a linear function of the daily rate of change on a day arbitrarily selected within the predetermined period and the daily rate of change on the current day, thereby showing the trend of the company's stock price as a line. A stock price prediction system characterized by the following features.

2. A program that predicts the stock price of a company, which is controlled by a computer. A base value setting step involves obtaining the closing stock price on the base date for the company to be predicted and setting that stock price as the base value, A stock price acquisition step involves acquiring the daily closing stock prices of the company for a predetermined period as daily stock prices and saving them in a record DB, A fluctuation rate calculation step which involves calculating the rate of change between the aforementioned reference value and the daily stock price stored in the record DB, and recording it in the storage DB as the daily fluctuation rate, A trend analysis step that analyzes the trend of the stock price of the company during the period to be predicted, based on the daily rate of change recorded in the storage DB, In order to execute, The trend analysis step involves using the daily rate of change recorded in the storage DB to perform an enthalpy transformation as a linear function of the daily rate of change on a day arbitrarily selected within the predetermined period and the daily rate of change on the current day, thereby showing the trend of the company's stock price as a line. A stock price prediction program characterized by the following features.

3. A stock price prediction system that predicts the stock price of a company, A stock price acquisition unit acquires the daily closing stock prices for a specified period for the companies to be predicted and stores them in a record database. A trend analysis unit analyzes the trend of the stock price of the company during the period to be predicted, based on the daily stock price recorded in the aforementioned record DB. Equipped with, The trend analysis unit uses the daily stock prices recorded in the record DB to perform an enthalpy transformation as a linear function of the daily stock price value on a day arbitrarily selected within the predetermined period and the daily stock price value on the current day, thereby showing the trend of the company's stock price as a line. A stock price prediction system characterized by the following features.

4. A program that predicts the stock price of a company, which is controlled by a computer. A stock price acquisition step involves obtaining the daily closing stock prices of the companies to be predicted for a predetermined period and saving them in a record database. A trend analysis step that analyzes the trend of the stock price of the company during the period to be predicted, based on the daily stock price recorded in the aforementioned record DB, In order to execute, The trend analysis step involves using the daily stock prices recorded in the record DB to perform an enthalpy transformation as a linear function of the daily stock price values ​​on arbitrarily selected days within the predetermined period and the daily stock price values ​​on the current day, thereby showing the trend of the company's stock price as a line. A stock price prediction program characterized by the following features.

Images