JP6501825B2 - INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM - Google Patents

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  In the past, techniques have been provided for generating indicator data that indicates the strength of a currency that is valid when trading multiple currency pairs. For example, for each of a plurality of currency pairs, there is provided a technique for calculating the difference in rate values of transactions of currency pairs at adjacent times and calculating indicator data of a designated currency.

JP, 2012-027513, A

  However, in the above-mentioned prior art, it is difficult to predict with high accuracy the transaction price of a financial product such as the rate value of the currency pair transaction. For example, it is not always possible to predict the rate value of the transaction of the currency pair with high accuracy only by calculating the difference between the rate values of the transaction of the currency pair at the adjacent time.

  This application is made in view of the above, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program for predicting a transaction price of a financial product with high accuracy.

  The information processing apparatus according to the present application is the time of the transaction price based on the acquisition unit that acquires information of the history regarding the transaction price of the financial product in which the transaction price changes, and the information of the history acquired by the acquisition unit. A second differential value prediction unit for predicting a second order differential value relating to the second order differential value, and a transaction price prediction unit for predicting the transaction price based on the second order differential value predicted by the second order differential value prediction unit. .

  According to one aspect of the embodiment, the transaction price of the financial product can be predicted with high accuracy.

FIG. 1 is a diagram illustrating an example of information processing by the information processing device 1 according to the embodiment. FIG. 2 is a diagram illustrating an exemplary configuration of the information processing apparatus according to the embodiment. FIG. 3 is a diagram showing an example of history information on the transaction price of the financial product according to the embodiment. FIG. 4 is a diagram showing an example of a model for predicting the transaction price of a financial product according to the embodiment. FIG. 5 is a diagram showing an example of detection of fluctuation exceeding a predetermined value in the transaction price of the financial product according to the embodiment. FIG. 6 is a diagram illustrating an exemplary configuration of a prediction unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the prediction of the transaction price of the financial product according to the embodiment. FIG. 8 is a flowchart illustrating an example of the procedure of learning processing in the learning unit according to the embodiment. FIG. 9 is a flowchart illustrating an example of a procedure of prediction regarding the transaction price of the financial product according to the embodiment. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus according to the embodiment.

  Hereinafter, a mode for carrying out an information processing apparatus and an information processing program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus and the information processing program according to the present application are not limited by this embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

[1. Example of Information Processing by Information Processing Device]
An example of information processing by the information processing device 1 according to the embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of information processing by the information processing device 1 according to the embodiment.

First, the information processing apparatus 1 shown in FIG. 1, the transaction price to get the financial instrument price X regarding history information _{X (t n) ··· X (} t n-m) that varies with respect to time t .

Here, t _n indicates, for example, the current time (the latest time). Further, t _{n + 1} indicates, for example, a time (a future time) one minute after the current time. Similarly, t _n-m indicates, for example, a time (past time) m minutes before the current time. Note that n and m are each independently an integer.

The history information X (t _n ) to X (t _{n -m} ) is information on the transaction price X of the financial product at time t _{n to} t _{n -m} (from the present to the past), respectively.

The history information X (t _n ) to X (t _{n -m} ) indicate, for example, the value of the transaction price X of the financial product at time t _{n to} t _{n -m} , respectively. The transaction price X of the financial instrument may be, for example, an exchange rate as shown in FIG.

Next, the information processing apparatus 1 relates to, for example, the time of the transaction price X at the future time t _{n + 1} based on the acquired information X (t _n )... X (t _n−m ) of the acquired history. The second derivative d ² X / dt ² (t _{n + 1} ) is predicted.

For example, the information processing apparatus 1 performs a second derivative using a model that predicts a second derivative d ² X / dt ² (t _{n + 1} ) from history information X (t _n )... X (t _n−m ). The second derivative value d ² X / dt ² (t _{n + 1} ) is predicted by obtaining a predicted value d ² X / dt ² ^ (t _{n + 1} ) of the value.

Next, the information processing apparatus 1 predicts the value X (t _{n + 1} ) of the transaction price X at a future time t _{n + 1} based on the above predicted second order differential value d ² X / dt ² (t _{n + 1} ). .

For example, the information processing apparatus 1, from the second floor the predicted value of the differential value _{^{d 2 X / dt 2 ^ (}} t n + 1), the calculation of the equation will be described later, trading predicted value for money _{X X ^ (t n + 1} ) by obtaining the , Predict the value X (t _{n + 1} ).

Thus, the information processing apparatus 1 predicts the second-order derivative value d ² X / dt ² (t _{n + 1} ) regarding the time of the transaction price X at the future time t _{n + 1} and also predicts the second-order derivative value d ² In order to predict the value X (t _{n + 1} ) of the transaction price X at a future time t _{n + 1} based on X / dt ² (t _{n + 1} ), the value X (t of the transaction price X of the financial instrument at a future time t _{n + 1 n + 1} ) can be predicted with high accuracy.

  That is, the information processing apparatus 1 predicts not the temporal fluctuation of the transaction price X such as the first-order differential value with respect to time but the temporal fluctuation of the temporal fluctuation of the transaction price X, that is, the second-order differential value with respect to time By obtaining the transaction price X from the predicted value of the value, the accuracy of the prediction has been improved compared to the prior art. In addition, the acceleration of the time change of the transaction price X of a financial instrument can be predicted by predicting the second-order derivative value regarding the time of the transaction price X of a financial instrument. Accordingly, it is possible to predict the magnitude and direction of the force that causes the time fluctuation of the transaction price X of the financial product. As described above, since the magnitude and direction of the force causing the time fluctuation of the transaction price X of the financial product can be predicted, the value of the transaction price X of the financial product can be predicted with high accuracy.

  The information processing apparatus 1 can communicate with the terminal device 3 by wire or wirelessly via, for example, a predetermined communication network (not shown). The terminal device 3 is, for example, a smartphone. The terminal device 3 can request the information processing device 1 to predict the value of the transaction price X.

When the information processing device 1 is requested by the terminal device 3 to predict the value of the transaction price X, the information processing device 1 may deliver the predicted value X ^ (t _{n + 1} ) of the transaction price X at time t _{n + 1} in the future to the terminal device 3 it can. The terminal device 3 receives the predicted value X ^ (t _{n + 1} ) of the transaction price X at a future time t _{n + 1} .

As a result, the user of the terminal device 3 can execute a transaction of a financial product based on the predicted value X ^ (t _{n + 1} ) of the transaction price X at the future time t _{n + 1} predicted with high accuracy.

[2. Configuration Example of Information Processing Device]
Next, a configuration example of the information processing apparatus 1 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing an example of the configuration of the information processing apparatus 1 according to the embodiment. As shown in FIG. 2, the information processing apparatus includes a communication unit 10, a storage unit 20, and a control unit 30.

  The information processing apparatus 1 includes an input unit (for example, a keyboard or a mouse) that receives various operations from the administrator of the information processing apparatus 1 and a display unit (for example, a liquid crystal display or the like) for displaying various information. You may have. The information processing apparatus 1 may be stand alone.

[2.1. Communication unit 10]
The communication unit 10 is realized by, for example, a network interface card (NIC). The communication unit 10 is connected to the network N in a wired or wireless manner, and transmits and receives information between, for example, the transaction apparatus 2 and the terminal device 3.

  The transaction apparatus 2 is an information processing apparatus that provides various services related to transactions of financial products in which the transaction price changes. The transaction apparatus 2 is realized by, for example, a server device or a cloud system.

  Here, as a financial product whose transaction price changes, for example, foreign exchange, stocks, government bonds, funds, insurance products, etc. may be mentioned. Examples of transaction prices of financial products include exchange rates, stock prices, government bond prices, fund dividends, and dividends on insurance products.

  In addition, since the stock price may be 0 yen, as a financial product in which the transaction price changes, foreign exchange in which the exchange rate changes continuously is preferable.

  For example, the transaction apparatus 2 distributes, to the information processing apparatus 1, information on the history of the transaction price of the financial product. Further, for example, the transaction apparatus 2 receives, from the information processing apparatus 1 or the terminal device 3, information on a transaction of a financial product, for example, information on an intention to buy and sell a financial product.

  Further, for example, the transaction apparatus 2 executes a transaction of a financial product according to the information on the transaction of the financial product received from the information processing apparatus 1 or the terminal device 3.

  The terminal device 3 is an information processing device used by a user. The terminal device 3 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, or a PDA (Personal Digital Assistant).

  For example, the terminal device 3 requests the information processing device 1 to predict the value of the transaction price of the financial product. In addition, for example, the terminal device 3 receives the predicted value of the transaction price of the financial product from the information processing device 1. In addition, the terminal device 3 distributes information on the transaction of the financial product, for example, information on the indication of intention to buy and sell the financial product, to the transaction apparatus 2.

[2.2. Storage unit 20]
The storage unit 20 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

  As shown in FIG. 2, the storage unit 20 includes a history information storage unit 21, a learning information storage unit 22, a detection information storage unit 23, a prediction information storage unit 24, a reception information storage unit 25, and a transaction information storage. And a unit 26.

  The history information storage unit 21 stores information on the history regarding the transaction price of the financial product.

  The learning information storage unit 22 stores information for executing a learning process and information on a model generated as a result of the learning process.

  The detection information storage unit 23 stores information on the predetermined value for the fluctuation of the transaction price of the financial instrument and the fluctuation of the detected transaction price of the financial instrument exceeding the predetermined value.

  The prediction information storage unit 24 stores information on the predicted transaction price of the financial product.

  The reception information storage unit 25 stores information on a request for prediction of the value of the transaction price of the financial product.

  The transaction information storage unit 26 stores a predetermined condition for the value of the predicted transaction price of the financial instrument and information on the transaction of the financial instrument for the predetermined condition.

[2.3. Control unit 30]
The control unit 30 is a controller, and for example, various programs (information processing program stored in a storage device inside the information processing apparatus 1 by a central processing unit (CPU), a micro processing unit (MPU), etc. (Corresponding to one example) is implemented by executing the RAM as a work area.

  Further, the control unit 30 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 2, the control unit 30 includes an acquisition unit 31, a learning unit 32, a detection unit 33, a prediction unit 34, a reception unit 35, a distribution unit 36, and a transaction processing unit 37. The control unit 30 implements or executes the function or action of the information processing described below.

[2.3.1. Acquisition unit 31]
The acquisition unit 31 acquires information on the history of the transaction price of a financial product whose transaction price changes. For example, the acquisition unit 31 acquires history information on the transaction price of a financial product from the transaction apparatus 2 via the network N and the communication unit 10.

  Here, the history information on the transaction price of the financial instrument is information on the transaction price of the financial instrument for each time in the period from the past to the present.

  The information on the transaction price of the financial product includes, for example, the value of the transaction price of the financial product, the first derivative of the transaction price of the financial product, and the second derivative of the transaction price of the financial product. Hereinafter, the first derivative of the transaction price of the financial product means the first derivative of the time of the transaction price of the financial instrument, and the second derivative of the transaction price of the financial product relates to the time of the transaction price of the financial instrument It means second derivative value.

  As the value of the transaction price of the financial instrument, for example, a set of high, low, open and close prices of the transaction price of the financial instrument, an average of high, low, open and close prices of the transaction price of the financial instrument, or A representative value such as a high price, a low price, an open price, or a close price of a transaction price of a financial instrument may be mentioned.

  For example, the acquisition unit 31 stores information of the acquired history in the history information storage unit 21.

  Here, an example of the information of the history regarding the transaction price of the financial product according to the embodiment will be described using FIG. 3. FIG. 3 is a diagram showing an example of history information on the transaction price of the financial product according to the embodiment.

  As illustrated in FIG. 3, the acquisition unit 31 acquires, for example, the value of the transaction price of the financial instrument for each time in the past period, for each type of transaction price of the financial instrument.

In the example shown in FIG. 3, the types of transaction prices of financial instruments are: high price X1 _H , low price X1 _L , open price X1 _S , close price X1 _E , high price X2 _H of stock price (X2), low price X2 _L, including opening price X2 _S, closing X2 _E, and high X3 _H of bonds (X3), low X3 _L, the opening value X3 _S, closing X3 _E.

The acquisition unit 31 determines the value X1 _H (t) of the transaction price of the financial product for each of the past times t = t _n−m , t _{n−m + 1} ... T _n−2 , t _n−1 , t _n. The table of X3 _E (t) is stored in the history information storage unit 21.

[2.3.2. Learning part 32]
Returning to FIG. 2, the learning unit 32 generates a model by performing supervised learning based on the history information on the transaction price of the financial product acquired by the acquisition unit 31.

  For example, the learning unit 32 reads out, from the history information storage unit 21, information on the history regarding the transaction price of the financial product. Also, for example, the learning unit 32 may use, for example, information for executing a learning process, such as information for executing a process such as back propagation (error back propagation method) in a neural network described later, from the learning information storage unit 22. read out.

For example, the learning unit 32 calculates correct answer information of the second-order derivative value of the transaction price of the financial product based on the information of the history regarding the transaction price of the financial product. For example, the learning unit 32 determines correct solution information d ² X / dt ² (t ₁ ) of the second derivative value of the transaction price of the financial product at a certain time t ₁ (l is an integer),
_{^{d 2 X / dt 2 (t}} l) = (X (t l) -2X (t l-1) + X (t l-2)) / Δt 2
Calculate according to the equation of Here, X (t _l ), X (t _l-1 ), and X (t _l-2 ) are financials at three adjacent times t _l , t _l-1 , and t _{l-2, respectively} . It is the value of the transaction price X of the product. Also, Δt is a time difference given by t _l −t _l−1 or t _l−1 −t _l−2 .

  For example, the learning unit 32 learns the relationship between the history information on the transaction price of the financial product and the correct information on the second floor differential value of the transaction price on the financial product, thereby obtaining the financial product from the information on the history on the transaction price of the financial product Generate a model that predicts the second derivative of the transaction price of.

Also, for example, the learning unit 32 calculates correct information of the first-order differential value of the transaction price of the financial product based on the information of the history regarding the transaction price of the financial product. For example, the learning unit 32 determines correct answer information dX / dt (t _l ) of the first-order derivative value of the transaction price of the financial product at a certain time t _l (l is an integer),
dX / dt (t ₁ ) = (X (t ₁ ) −X (t _{1 −1} )) / Δt
Calculate according to the equation of Here, X (t _l ) and X (t _{l -1} ) are the values of the transaction price X of the financial instrument at two adjacent times t _l and t _{l -1} , respectively. Also, Δt is a time difference given by t _l −t _l−1 .

  For example, the learning unit 32 learns from the information on the history of the transaction price of the financial product by learning the relationship between the information on the history of the transaction price of the financial product and the correct information on the first floor differential value of the transaction price of the financial product. Generate a model that predicts the first derivative of the transaction price of a product.

  For example, when the history information on the transaction price of the financial product includes information on high, low, open, and close prices of the transaction price of the financial product for each time in the period from the past to the present, the learning unit 32 Information on the high, low, open, and close prices of the transaction price of the financial instrument for each time in the past period, and the (for example, the closing) second-order derivative value or first-order derivative correct information of the transaction price of the financial instrument Learn relationships

  For example, when the history information on the transaction price of a financial product includes information on the transaction price of a financial product in a past fixed period, the learning unit 32 generates information and finance on the transaction price of a financial product in a past fixed period. The relationship with the second order differential value of the transaction price of the product or the correct information of the first order differential value is repeatedly learned for a plurality of fixed periods.

  Note that a model that predicts the second derivative or first derivative of the transaction price of a financial product from historical information on the transaction price of a financial product is the time to predict the second derivative or first derivative of the transaction price of a financial product And it may be a plurality of models having different time widths.

  For example, the above model may be a model that predicts a second derivative value or a first derivative value of the transaction price of a financial instrument at time s minutes from the current time (s is an integer). Also, for example, the above model is a model that predicts the average value of the second derivative value or the first derivative value of the transaction price of the financial instrument for t minutes (t is an integer) after time s minutes from the current time, It is also good.

  The learning unit 32 is, for example, a neural network in which layers having a plurality of nodes are connected in multiple stages, and may be a DNN (Deep Neural Network) realized by a so-called deep learning technique.

  For example, the learning unit 32 generates a non-linear model by the following learning method using deep learning technology. For example, the learning unit 32 initializes the coupling coefficient between each node in the neural network and accepts input of history information on the transaction price of a financial product.

  Then, the learning unit 32 generates a non-linear model by processing such as back propagation (error back propagation method). In backpropagation, it is desired to minimize the value of a predetermined error function between the input of historical information on the transaction price of the financial instrument and the output of the second derivative or first derivative of the transaction price of the financial instrument. Adjust the coupling factor.

  In this manner, the learning unit 32 generates a non-linear model of predicted values for historical information on the transaction price of a financial product.

  For example, the learning unit 32 stores in the learning information storage unit 22 a model generated as a result of the learning process, that is, a model generated by performing supervised learning on information on a history of a transaction price of a financial product. Do.

  Here, an example of a model for predicting the transaction price of a financial product according to the embodiment will be described using FIG. 4. FIG. 4 is a diagram showing an example of a model for predicting the transaction price of a financial product according to the embodiment.

  As shown in FIG. 4, for example, the learning unit 32 generates a plurality of types of models for each type of transaction price of a financial product.

  In the example shown in FIG. 4, the types of transaction prices of financial instruments include foreign exchange (X1), stock price (X2), and government bonds (X3) as shown in FIG. In the example shown in FIG. 4, the types of models are model 1A, model 1B and model 1C for exchange (X1) and model 2A, model 2B and model 2C for stock price (X2), as described later. Includes Model 3A, Model 3B, and Model 3C for government bond (X3).

  Here, Model 1A, Model 2A, and Model 3A are models for predicting the second-order derivative value of the transaction price of the financial product from the information of the history regarding the transaction price of the financial product.

  In addition, Model 1 B, Model 2 B, and Model 3 B are models for predicting the second-order derivative value and first-order derivative value of the transaction price of the financial product from the history information on the transaction price of the financial product.

  The models 1C, 2C, and 3C are models for predicting the second-order differential value of the transaction price of a plurality of financial products from historical information on the transaction prices of a plurality of financial products. The model 1C is a model which predicts second derivative values of a plurality of exchange rates from, for example, a plurality of exchange rates between the Japanese yen, the US dollar, the euro, the Chinese yuan, and the like. For example, the model 2C is, for example, a model that predicts second-order derivatives of the stock prices of a plurality of stock companies from the stock prices of a plurality of stock companies.

  The learning unit 32 stores the table of model 1A ... model 3C generated for the exchange (X1), the stock price (X2), and the national bond (X3) as the transaction price of the financial product in the learning information storage unit 22.

[2.3.3. Detection unit 33]
Returning to FIG. 2, based on the information on the history of the transaction price of the financial product acquired by the acquisition unit 31, the detection unit 33 detects a change in the transaction price of the financial product that exceeds a predetermined value.

  For example, the detection unit 33 reads out, from the history information storage unit 21, information on the history regarding the transaction price of the financial product. In addition, for example, the detection unit 33 reads a predetermined value (threshold) for the fluctuation of the transaction price of the financial product from the detection information storage unit 23.

  For example, the detection unit 33 detects a change in the transaction price of the financial product exceeding a predetermined value by determining whether or not the value of the change in the transaction price of the financial product at a certain time exceeds a predetermined value (threshold). .

  For example, if the historical information on the transaction price of the financial product is the value of the transaction price of the financial product, the value of the change in the transaction price of the financial product is the first-order derivative value of the transaction price of the financial product.

  For example, if the historical information on the transaction price of the financial product is the first floor differential value of the transaction price of the financial product, then the value of the change in the transaction price of the financial product is the second floor differential value of the transaction price of the financial product is there.

  For example, if the historical information on the transaction price of the financial product is the second-order derivative of the transaction price of the financial product, then the value of the change in the transaction price of the financial product is the third-order derivative of the transaction price of the financial product is there.

  For example, the detection unit 33 stores, in the detection information storage unit 23, information related to the fluctuation exceeding the predetermined value of the transaction price of the detected financial product. Specifically, the detection unit 33 determines a predetermined value for the fluctuation of the transaction price of the financial instrument, a value of fluctuation of the transaction price of the financial instrument exceeding the predetermined value (threshold), and a transaction price of the financial instrument exceeding the predetermined value (threshold). , And information on the transaction price of the financial instrument at that time.

  Here, an example of the detection of the fluctuation exceeding the predetermined value in the transaction price of the financial product according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram showing an example of detection of fluctuation exceeding a predetermined value in the transaction price of the financial product according to the embodiment.

  In FIG. 5, the horizontal axis indicates time t, and the vertical axis indicates the value of the fluctuation V of the transaction price X of the financial instrument, that is, the first derivative of the transaction price X of the financial instrument. The absolute value of the first-order derivative value of the transaction price X of the financial product may be used as the value of the fluctuation V of the transaction price X of the financial product. In FIG. 5, the predetermined value Vth means a threshold for the value of the fluctuation V of the transaction price X of the financial instrument.

  In the example shown in FIG. 5, the values V (t ′) and V (t ′ ′) of the fluctuation V of the transaction price X of the financial product at time t ′ and time t ′ ′ exceed the predetermined value Vth. The detection unit 33 detects values V (t ′) and V (t ′ ′) of fluctuations exceeding the predetermined value Vth of the transaction price X of the financial product at time t ′ and time t ′ ′.

[2.3.4. Prediction unit 34]
Returning to FIG. 2, the prediction unit 34 predicts the value of the transaction price of the financial product in the future, based on the information on the history of the transaction price of the financial product acquired by the acquisition unit 31.

  For example, the prediction unit 34 reads out, from the history information storage unit 21, information on the history regarding the transaction price of the financial product. Also, for example, the prediction unit 34 reads, from the learning information storage unit 22, information on a model generated as a result of the learning process. Also, for example, the prediction unit 34 reads, from the detection information storage unit 23, information related to the fluctuation exceeding the predetermined value of the transaction price of the financial product.

  Here, a configuration example of the prediction unit 34 according to the embodiment will be described with reference to FIG. FIG. 6 is a diagram illustrating an exemplary configuration of a prediction unit according to the embodiment. As shown in FIG. 6, the prediction unit 34 includes a second-order derivative prediction unit 34a, a first-order derivative prediction unit 34b, a transaction price prediction unit 34c, a price fluctuation prediction unit 34d, and a processing unit 34e.

[2.3.4.1. Second derivative value prediction unit 34a]
The second-order derivative value prediction unit 34a predicts a second-order derivative value of the transaction price of the financial product in the future, based on the information on the history of the transaction price of the financial product acquired by the acquisition unit 31.

  For example, the second derivative value prediction unit 34a predicts the second derivative value of the transaction price of the financial product in the future, using a neural network learned by the information on the history of the transaction price of the financial product.

  For example, the second derivative value prediction unit 34a predicts the second derivative value of the transaction price of the financial product in the future by inputting information on the history of the transaction price of the financial product into the model generated by the learning unit 32.

  For example, when the history information on the transaction price of the financial product includes information on the transaction price of the financial product in a predetermined period in the past, the second-order differential value prediction unit 34a determines information on the transaction price of the financial product in the predetermined period in the past Predict the second derivative of the transaction price of financial instruments in the future.

  For example, the second derivative value prediction unit 34a inputs information on the transaction price of a financial product in a past fixed period in a model generated using the information on the transaction price of a financial product in the past fixed period in the learning unit 32. By this, we predict the second derivative of the transaction price of financial instruments in the future.

  In addition, the past fixed period of the information regarding the transaction price of the financial product in the past fixed period used when preparing a model in the learning unit 32 is used when predicting the second-order derivative value of the transaction price of the financial product in the future Have the same time width as the past fixed period of information on the transaction price of the financial instrument in the past fixed period.

  For example, if historical information on the transaction price of a financial product includes information on high, low, open, and close prices of the transaction price for each time in the period from the past to the present, second-order derivative value prediction The unit 34a predicts the second derivative value of the transaction price of the financial instrument in the future based on the information of the high price, the low price, the open price, and the close price of the transaction price of the financial instrument for each time in the period from the past to the present.

  For example, the second derivative value prediction unit 34a uses the learning unit 32 to obtain information on the high price, low price, open price, and close price of the transaction price of the financial product for each time in the period from the past to the present. The second derivative of the transaction price of the financial instrument in the future is predicted by inputting into the model generated using the information of the low price, the open price, and the close price.

  For example, when the detection unit 33 detects a change in the transaction price of a financial product that exceeds a predetermined value, the second-order differential value prediction unit 34a excludes information with a change exceeding the predetermined value detected by the detection unit 33. The second derivative of the transaction price of the financial instrument in the future is predicted based on the information of the history.

  For example, the learning unit 32 learns the relationship between the history information on the transaction price of the financial product excluding the information accompanied by the variation exceeding the detected predetermined value and the correct information of the second-order differential value of the transaction price of the financial product. .

  The second derivative value prediction unit 34a inputs future information on the transaction price of the financial product excluding the information accompanied by the variation exceeding the detected predetermined value into the model generated by the learning unit 32 to obtain financial in the future. Predict the second derivative of the commodity's transaction price.

  In the example illustrated in FIG. 5, the second-order differential value prediction unit 34 a calculates the value V (t of fluctuation exceeding the predetermined value Vth detected by the detection unit 33 from the information X (t) of the history related to the transaction price X of the financial product. Exclude the values X (t ') and X (t ") of the transaction price X of the financial instrument, which is information accompanied by') and V (t").

  Then, the second derivative value prediction unit 34a determines the value of the transaction price X of the financial product, which is information accompanied by the values V (t ′) and V (t ′ ′) of fluctuations exceeding the predetermined value Vth detected by the detection unit 33. Based on historical information X (t) on the transaction price X of the financial instrument excluding X (t ′) and X (t ′ ′), a second derivative of the transaction price X of the financial instrument is predicted.

[2.3.4.2. First-order derivative value prediction unit 34b]
The first-order derivative value prediction unit 34 b predicts the first-order derivative value of the transaction price of the financial product in the future, based on the information on the history of the transaction price of the financial product acquired by the acquisition unit 31.

  For example, the first-order derivative prediction unit 34b, like the second-order derivative prediction unit 34a, uses the neural network learned from the information on the history of the transaction price of the financial product to obtain the first derivative of the transaction price of the financial product in the future Predict the value.

  For example, as in the case of the second derivative prediction 34a, the first derivative estimating unit 34b inputs future information on the transaction price of the financial instrument into the model generated by the learning unit 32, thereby trading the financial instruments in the future. Predict the first derivative of the price.

  For example, when the history information on the transaction price of a financial product includes information on the transaction price of a financial product in a past fixed period, the first-order differential value prediction unit 34b, like the second-order differential value prediction unit 34a, The first derivative value of the transaction price of the financial instrument in the future is predicted based on the information on the transaction price of the financial instrument in a fixed period of time.

  For example, if the historical information about the transaction price of a financial product includes high, low, open, and close prices of the transaction price of the financial product for each time in the period from the past to the present, the first-order derivative value The prediction unit 34b, similar to the second-order derivative prediction unit 34a, is a financial product in the future based on information on the high price, the low price, the open price, and the close price of the transaction price for each time in the period from the past to the present. Predict the first derivative of the transaction price of.

  For example, when the detection unit 33 detects a change in the transaction price of a financial product exceeding a predetermined value, the first-order derivative prediction unit 34b detects the first-order derivative prediction unit 34a as in the second-order derivative prediction unit 34a. Based on historical information excluding information accompanied by fluctuations exceeding a predetermined value, a first-order derivative value of a transaction price of a financial instrument in the future is predicted.

[2.3.4.3. Transaction Price Forecasting Unit 34c]
The transaction price prediction unit 34c predicts the value of the transaction price X of the financial instrument in the future based on the second order differential value predicted by the second order differential value prediction unit 34a.

For example, the transaction price prediction unit 34c may calculate the time difference Δt between the past time t _n-1 (for example, the current one minute ago) and the current time t _n , the current time t _n and the future time t _{n + 1} In the case where the time difference Δt is constant, the predicted value X ^ (t _{n + 1} ) of the transaction price X of the financial instrument at a future time t _{n + 1} (for example, the current one minute later) is X ^ (t _{n + 1} ) = 2 × (t _n ) −x (t _n−1 ) + d ² x / dt ² ^ (t _{n + 1} ) × Δt ²
Calculate according to

Here, X (t _n-1 ) is the value of the transaction price X of the financial instrument at the past time t _{n -1} . Also, X (t _n ) is the value of the transaction price X of the financial instrument at the current time t _n . Further, d ² X / dt ² ^ (t _{n + 1} ) is a predicted value of the second derivative of the transaction price X of the financial instrument at a future time t _{n + 1} .

The transaction price prediction unit 34c can obtain X (t _{n + 1} ) with high accuracy as the time difference Δt is smaller.

  For example, the transaction price prediction unit 34c determines the future transaction price of a financial product based on the second derivative value predicted by the second derivative value predictor 34a and the first derivative value predicted by the first derivative value predictor 34b. It may be predicted.

For example, when the time difference Δt between the past time t _n-1 and the current time t _n and the time difference Δt between the current time t _n and the future time t _{n + 1} are constant, the transaction price prediction unit 34 c The predicted value X ^ (t _{n + 1} ) of the transaction price X of the financial instrument at time t _{n + 1} of X ^ (t _{n +1} ) = X (t _n + ₁ ) + 2 dX / dt ^ (t _{n + 1} ) x Δt-d ² X / dt ² ^ (t _{n + 1} ) × Δt ²
Calculate according to

Here, X (t _n-1 ) is the value of the transaction price X of the financial instrument at the past time t _{n -1} . Further, dX / dt ^ (t _{n + 1} ) is a predicted value of the first derivative of the transaction price X of the financial instrument at a future time t _{n + 1} . Further, d ² X / dt ² ^ (t _{n + 1} ) is a predicted value of the second derivative of the transaction price X of the financial instrument at a future time t _{n + 1} .

It should be noted that the transaction price prediction unit 34c may calculate the predicted value X ^ (t _{n + 1} ) of the transaction price X of the financial instrument at a future time t _{n + 1} according to a formula different from the formula described above. Further, the value of the transaction price X of the financial instrument in the future predicted in the transaction price prediction unit 34c is not limited to the value of the transaction price X of the financial instrument at the time after the current one minute.

  For example, the transaction price prediction unit 34c repeats the prediction of the value of the transaction price X of the financial product at a time after one minute, thereby making it possible to perform the financing at the current time after s minutes (s is an integer of 2 or more). It is possible to predict the value of the transaction price X of a product.

  For example, the transaction price prediction unit 34c similarly trades a financial instrument for t minutes (t is an integer of 1 or more) from the current time after s minutes (s is an integer of 2 or more) The values of prices X and their average value can be predicted.

  Here, an example of the prediction of the transaction price of the financial product according to the embodiment will be described using FIG. 7. FIG. 7 is a diagram illustrating an example of the prediction of the transaction price of the financial product according to the embodiment. In FIG. 7, the horizontal axis indicates time t, and the vertical axis indicates the value of the transaction price X of the financial instrument. The time t may be a UNIX (registered trademark) time.

In FIG. 7, the solid line indicates the actual data of the transaction price (exchange rate) X of the financial product, and the dotted line indicates the result of prediction by the information processing device 1. In FIG. 7, the actual data of the trading price of financial instruments from the past of time t _n-m until the current time t _n is shown.

In the example illustrated in FIG. 7, the learning unit 32 which is a neural network determines the past fixed period T from time t _{n -k-10} to time t _{n -k-1} (10 minutes before time t _{n -k} ) Value X (t _{n -k -10} ) ... X (t _n-k-1 ) of the transaction price X of the financial product at the second and second derivative value d ² x of the transaction price X of the financial product at time t _n-k The relationship between / dt ² (t = t _n−k ) and the correct answer information is repeatedly learned for k = 0. For example, the learning unit 32 performs learning in one-minute intervals using data for 14 years.

Thereby, the learning unit 32, model d ^{2 x} / dt ^{2 (t} of predicting second-order differential value of the transaction price of financial instruments at transaction price X value from a predetermined time of the financial instruments at a predetermined time prior to 10 minutes = T _{n -k} ) = f (X (t _{n -k -10} )... X (t _{n -k-1} )) is generated. Here, f is a non-linear function that represents a model.

  As described above, it is preferable to use a recursive neural network for the learning unit 32 because the learning unit 32 repeatedly learns based on time-series data.

Next, the second derivative value prediction unit 34a predicts the second derivative value d ² X / dt ² (t _{n + 1} ) of the transaction price X of the financial product at time t _{n + 1} using the model generated by the learning unit 32. .

The transaction price prediction unit 34c, based on the second derivative value d ² X / dt ² (t _{n + 1} ) of the transaction price X of the financial product at time t _{n + 1} predicted by the second derivative value prediction unit 34a, for example, The value X (t _{n + 1} ) of the transaction price X of the financial instrument at time t _{n + 1} is predicted according to

In FIG. 7, the information processing apparatus is used for actual data X (t _n-m ) ... X (t _n ) of the transaction price of the financial product from the past time t _n-m to the current time t _n. 1 shows the similarly predicted result. The result of the prediction shown in FIG. 7 indicates that the information processing apparatus 1 can predict the value of the transaction price X of a financial product with high accuracy.

As described above, in the information processing apparatus 1, the second derivative value prediction unit 34 a determines the value X of the transaction price X of the financial product for each fixed period T (t _{n−k −10} ... T _n−k−1 ) in the past. (T _n−k−10 )... X (t _n−k−1 ) The second derivative value d ² of the transaction price X of the financial instrument at time t _n−k after the elapse of a predetermined period T in the past _{^{x / dt 2 (t = t}} n-k) second-order differential value transaction price prediction unit 34c while prediction is predicted to ^{d 2 x / dt 2 (t} = t n-k) past predetermined period T on the basis of the The value X (t _n-k ) of the transaction price X of the financial instrument at time t _n-k after the lapse of t may be estimated.

  In the information processing apparatus 1, the second-order derivative prediction unit 34 a may use the value of the transaction price of the financial product for each fixed period in the past (which may include the present) at a time after the next fixed period. Even if the second differential value of the transaction price is predicted and the transaction price prediction unit 34c is configured to predict the value of the transaction price of the financial instrument at the time after the next predetermined period based on the predicted second differential value, Good.

  Further, in the information processing apparatus 1, the second-order differential value prediction unit 34 a may perform financial processing at a time after a longer period than a predetermined period based on the value of the transaction price of the financial product for each fixed period in the past (which may include the present). As it predicts the second-order derivative value of the transaction price of the product, and also predicts the value of the transaction price of the financial instrument at a time after a period longer than the predetermined period based on the predicted second-order derivative value. It may be configured.

Also, for example, the second derivative value prediction unit 34a may use information X1 _H (t) ... X3 _E (t) (t = t _n- ) of history regarding transaction prices of a plurality of financial products as illustrated in FIG. 3. _.. , t _{n− 2} , t _n−1 , t _n ) are input to a plurality of models 1A,..., model 3C as shown in FIG.

  Thereby, the second derivative value prediction unit 34a predicts second derivative values or the like of the transaction prices X1, X2, and X3 of a plurality of financial products. The transaction price prediction unit 34c predicts the values of the transaction prices X1, X2, and X3 of the plurality of financial products based on the second-order derivatives of the plurality of financial products and the transaction prices X1, X2, and X3.

  As described above, in the information processing apparatus 1, the second-order differential value prediction unit 34 a predicts second-order differential values etc. of the transaction prices of a plurality of financial products based on the information of the history of the transaction prices of the plurality of financial products The unit 34c may be configured to predict the transaction prices of a plurality of financial instruments based on second-order derivatives of the transaction prices of the plurality of financial instruments.

  In the information processing apparatus 1, the second-order derivative value predicting unit 34a predicts the second-order derivative value and the like of the transaction prices of a plurality of financial products based on the information of the history of the transaction prices of a plurality of financial products. May be configured to predict the transaction price of a single financial instrument based on the second derivative of the transaction prices of a plurality of financial instruments.

[2.3.4.4. Price fluctuation forecasting unit 34d]
Returning to FIG. 6, the price fluctuation prediction unit 34 d predicts a fluctuation exceeding the predetermined value of the transaction price of the financial product in the future, based on the information on the history of the transaction price of the financial product acquired by the acquisition unit 31.

  For example, the price fluctuation prediction unit 34d uses information with fluctuations exceeding the predetermined value of the transaction price of the financial instrument in the past, which is included in the information on the history of the transaction price of the financial instrument, to convert the transaction price of the financial instrument in the future. Predict variations above a predetermined value.

[2.3.4.5. Processing unit 34e]
The processing unit 34e executes a predetermined process in accordance with the fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit 34d. The processing unit 34e includes a prediction stopping unit 34f and a prediction interpolation unit 34g.

  The prediction stopping unit 34 f stops the prediction of the second-order derivative value by the second-order derivative value predicting unit 34 a in a period corresponding to the fluctuation exceeding the predetermined value predicted by the price fluctuation predicting unit 34 d. For example, the prediction stop unit 34 f transmits a signal to display the stop of the prediction of the transaction price of the financial product on the display of the terminal device 3 via the communication unit 10 and the network N.

  Alternatively, the prediction stopping unit 34f does not stop the second-order differential value prediction by the second-order differential value predicting unit 34a in the period corresponding to the fluctuation exceeding the predetermined value predicted by the price fluctuation predicting unit 34d. Processing may be stopped.

  The prediction interpolation unit 34g interpolates the prediction of the second-order derivative value by the second-order derivative value prediction unit 34a in a period corresponding to the fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit 34d.

  For example, the prediction interpolation unit 34g interpolates the prediction of the second-order derivative value using the average value of the second-order derivative values before and after the period corresponding to the fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit 34d. Alternatively, for example, the prediction interpolation unit 34g continuously interpolates prediction of second derivative values using second derivative values before and after a period corresponding to fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit 34d.

  For example, the transaction price prediction unit 34c predicts the transaction price of the financial product based on the second order differential value predicted by the second order differential value prediction unit 34a and the second order differential value interpolated by the prediction interpolation unit 34g.

  For example, the prediction unit 34 stores the value of the predicted transaction price of the financial product in the prediction information storage unit 24.

  The information on the transaction price of the financial product predicted by the prediction unit 34 includes the second-order differential value of the transaction price of the financial product predicted by the second-order differential value prediction unit 34a, the financial product predicted by the first-order differential value prediction unit 34b Value of the transaction price of the financial product predicted by the transaction price prediction unit 34c, and the value of the fluctuation exceeding the predetermined value of the transaction price of the financial product predicted by the price fluctuation prediction unit 34d, etc. Can be mentioned.

[2.3.5. Reception unit 35]
The receiving unit 35 receives, from the terminal device 3 via the network N and the communication unit 10, information on a request for prediction of the value of the transaction price of the financial product.

  The information on the demand for forecasting the value of the transaction price of the financial instrument includes, for example, the type of financial instrument, the type of value of the transaction price of the financial instrument, the date, time, and time, etc. involved in forecasting the transaction price. Can be mentioned.

  For example, the reception unit 35 stores, in the reception information storage unit 25, information on a request for prediction of the value of the transaction price of the financial product.

[2.3.6. Distribution unit 36]
When the accepting unit 35 receives information on a request for prediction of the value of the transaction price of the financial product, the distributing unit 36 receives the value of the transaction price of the financial product predicted by the transaction price predicting unit 34c in the predicting unit 34. Are distributed to the terminal device 3 via the communication unit 10 and the network N.

[2.3.7. Transaction processing unit 37]
For example, the transaction processing unit 37 transmits, to the transaction apparatus 2 via the communication unit 10 and the network N, information on a transaction of a financial product, for example, information on an intention to buy and sell a financial product.

  For example, the transaction processing unit 37 reads, from the transaction information storage unit 26, a predetermined condition for the value of the transaction price of the financial product predicted by the transaction price prediction unit 34c in the prediction unit 34.

  Then, the transaction processing unit 37 determines whether the value of the transaction price of the financial product predicted by the transaction price prediction unit 34c in the prediction unit 34 satisfies a predetermined condition.

  The transaction processing unit 37 transmits the financial product to the transaction apparatus 2 via the communication unit 10 and the network N when the value of the transaction price of the financial product predicted by the transaction price prediction unit 34c in the prediction unit 34 satisfies a predetermined condition. Send information about your transaction.

  For example, if the value of the transaction price of the financial instrument predicted by the transaction price forecasting unit 34c is higher (lower) than the predetermined value or the current transaction price of the financial instrument, the transaction processing unit 37 Send information about the intention to sell (buy) financial products.

  Alternatively, for example, the value of the error function when the transaction processing unit 37 generates a model for predicting the second derivative value of the transaction price of the financial product from the information on the history of the transaction price of the financial product in the learning unit 32 has a predetermined value In the case of being larger (smaller), it may be configured to transmit information regarding the intention not to buy and sell (trade) the financial instrument to the trading device 2.

  The transaction processing unit 37 stores, in the transaction information storage unit 26, information related to a transaction of a financial product under a predetermined condition, for example, information related to an intention to buy and sell a financial product.

[3. Procedure of learning process]
Next, an example of the procedure of the learning process in the learning unit according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of the procedure of learning processing in the learning unit according to the embodiment.

  As shown in FIG. 8, first, the learning unit 32 in the information processing device 1 acquires history information on the transaction price of the financial product (step S101).

  Thereafter, the learning unit 32 calculates correct answer information such as the second-order derivative value of the transaction price of the financial product (step S102).

  Thereafter, the learning unit 32 performs a model so as to minimize the value of the error function between the second derivative of the transaction price of the financial product output from the learning unit 32 and the correct information such as the second derivative of the transaction price. Are generated (step S103).

  Thereafter, the learning unit 32 determines whether the value of the error function satisfies a predetermined condition (step S104). When the value of the error function satisfies the predetermined condition (step S104: Yes), the learning unit 32 ends the learning process. If the value of the error function does not satisfy the predetermined condition (step S104: No), the learning unit 32 returns to step S103.

[4. Procedure of forecasting of transaction price]
Next, an example of the procedure of prediction regarding the transaction price of the financial product according to the embodiment will be described using FIG. FIG. 9 is a flowchart illustrating an example of a procedure of prediction regarding the transaction price of the financial product according to the embodiment.

  As shown in FIG. 9, first, the information processing apparatus 1 acquires information of a history regarding a transaction price of a financial product (step S201).

  Thereafter, the information processing device 1 determines whether or not a fluctuation exceeding the predetermined value of the transaction price of the financial product is detected (step S202).

  If it is detected that the transaction price of the financial product exceeds the predetermined value (Step S202: Yes), the information processing device 1 proceeds to Step S203.

  Thereafter, the information processing device 1 excludes the information with the fluctuation of the transaction price exceeding the predetermined value from the information of the history regarding the transaction price of the financial product (step S203).

  If the fluctuation of the transaction price of the financial product exceeding the predetermined value is not detected (step S202: No), the information processing device 1 proceeds to step S204.

  Thereafter, the information processing device 1 predicts the second-order derivative value and the like of the transaction price of the financial product (step S204).

  Thereafter, the information processing device 1 predicts the value of the transaction price of the financial product (step S205).

  Thereafter, the information processing device 1 determines whether a request for prediction of the value of the transaction price of the financial product has been received (step S206).

  When the request for prediction of the value of the transaction price of the financial product is received (step S206: Yes), the information processing device 1 proceeds to step S207.

  Thereafter, the information processing device 1 distributes the value of the predicted transaction price of the financial product (step S207).

  If the request for prediction of the value of the transaction price of the financial product is not received (step S206: No), the information processing device 1 proceeds to step S208.

  Thereafter, the information processing device 1 determines whether or not the value of the predicted transaction price of the financial product satisfies a predetermined condition (step S208).

  If the value of the predicted transaction price of the financial product satisfies the predetermined condition (step S208: Yes), the information processing device 1 proceeds to step S209.

  Thereafter, the information processing device 1 executes transaction processing of a financial product (step S209).

  If the value of the predicted transaction price of the financial product does not satisfy the predetermined condition (step S208: No), the information processing device 1 ends the process of predicting the transaction price of the financial product.

[5. Hardware configuration]
The information processing apparatus 1 according to the embodiment described above is realized by, for example, a computer 100 configured as shown in FIG. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus 1 according to the embodiment. The computer 100 includes a CPU 110, a RAM 120, a ROM 130, an HDD (Hard Disk Drive) 140, a media interface (I / F) 150, a communication interface (I / F) 160, and an input / output interface (I / F) 170.

  The CPU 110 operates based on a program stored in the ROM 130 or the HDD 140 to control each part. The ROM 130 stores a boot program executed by the CPU 110 at startup of the computer 100, a program depending on the hardware of the computer 100, and the like.

  The HDD 140 stores a program executed by the CPU 110, data used by the program, and the like.

  The media interface 150 reads a program or data stored in the recording medium 180 and provides the CPU 110 via the RAM 120. The CPU 110 loads such a program from the recording medium 180 onto the RAM 120 via the media interface 150, and executes the loaded program. The recording medium 180 is, for example, an optical recording medium such as a digital versatile disc (DVD) or a phase change rewritable disk (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  The communication interface 160 receives data from another device via the network N and sends it to the CPU 110, and provides the data generated by the CPU 110 to the other device via the network N.

  The CPU 110 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 170. The CPU 110 acquires data from an input device via the input / output interface 170. The CPU 110 also outputs the generated data to the output device via the input / output interface 170.

  For example, when the computer 100 functions as the information processing apparatus 1 according to the embodiment, the CPU 110 of the computer 100 implements the function of the control unit 30 by executing a program loaded on the RAM 120. The CPU 110 of the computer 100 reads these programs from the recording medium 180 and executes them, but as another example, these programs may be acquired from another device via the network N.

  In addition, the above-described information processing apparatus 1 may be realized by a plurality of server computers, or, depending on the function, may be realized by calling an external platform or the like by API (Application Programming Interface) or network computing. Can be changed flexibly.

[6. effect〕
As described above, the information processing apparatus 1 according to the embodiment includes the acquisition unit 31, the second-order differential value prediction unit 34a, and the transaction price prediction unit 34c. The acquisition unit 31 acquires information on the history of the transaction price of a financial product whose transaction price changes. The second-order derivative value predicting unit 34 a predicts a second-order derivative value regarding the time of the transaction price based on the information of the history acquired by the acquiring unit 31. The transaction price prediction unit 34c predicts the transaction price based on the second-order differential value predicted by the second-order differential value prediction unit 34a.

  As described above, the information processing apparatus 1 according to the embodiment predicts the second-order derivative value regarding the time of the transaction price of the financial product based on the information of the history, and the transaction price of the financial product based on the predicted second-order derivative value. Since it predicts, the transaction price of the financial product can be predicted with high accuracy.

  The information processing apparatus 1 according to the embodiment further includes a first-order derivative value prediction unit 34 b. The first-order derivative value prediction unit 34 b predicts the first-order derivative value regarding the time of the transaction price based on the information of the history acquired by the acquisition unit 31. The transaction price prediction unit 34c predicts the transaction price based on the second order differential value predicted by the second order differential value prediction unit 34a and the first order differential value predicted by the first order differential value prediction unit 34b.

  As described above, the information processing apparatus 1 according to the embodiment predicts the second derivative value and the first derivative value regarding the time of the transaction price of the financial product based on the information of the history, and the predicted second derivative value and the estimated first derivative value. Since the trading price of the financial product is predicted based on both of the first-order derivatives, the trading price of the financial product can be predicted with higher accuracy.

  Further, in the information processing apparatus 1, the information on the history includes information on the transaction price in the past fixed period. The second derivative value prediction unit 34a predicts a second derivative value regarding the time of the transaction price based on the information regarding the transaction price in a past fixed period.

  As described above, since the information processing apparatus 1 according to the embodiment predicts the second-order differential value regarding the time of the transaction price of the financial product based on the information regarding the transaction price of the financial product in the past fixed period, the transaction of the financial product It is possible to easily predict the second derivative value of the price with respect to time and to easily predict the transaction price of a financial product with high accuracy.

  Further, in the information processing device 1, the second-order differential value prediction unit 34a predicts the second-order differential value regarding the time of the transaction price using the neural network learned by the information of the history.

  As described above, since the information processing apparatus 1 according to the embodiment predicts the second-order differential value regarding the time of the transaction price using the neural network learned by the information of the history regarding the transaction price of the financial product, the transaction price of the financial product The second derivative with respect to time of time can be predicted with high accuracy, and the transaction price of the financial product can be predicted with higher accuracy.

  The information processing apparatus 1 according to the embodiment further includes a detection unit 33. The detection unit 33 detects, based on the information of the history acquired by the acquisition unit 31, a fluctuation in which the transaction price exceeds a predetermined value. The second order differential value prediction unit 34a predicts a second order differential value regarding the time of the transaction price based on the information of the history excluding the information accompanied by the fluctuation exceeding the predetermined value detected by the detection unit 33.

  Thus, the information processing apparatus 1 according to the embodiment determines the second-order derivative value regarding the time of the transaction price of the financial product based on the information of the history excluding the information accompanied by the fluctuation exceeding the predetermined value of the transaction price of the financial product. As it is forecasting, it is possible to predict with high precision the second derivative value of the trading price of the financial product with respect to time and to predict the trading price of the financial product with higher precision.

  The information processing apparatus 1 according to the embodiment further includes a price fluctuation prediction unit 34 d and a processing unit 34 e. The price fluctuation prediction unit 34 d predicts the fluctuation of the transaction price exceeding a predetermined value based on the information of the history acquired by the acquisition unit 31. The processing unit 34e executes a predetermined process in accordance with the fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit 34d.

  As described above, the information processing apparatus 1 according to the embodiment predicts the fluctuation of the transaction price exceeding the predetermined value based on the information of the history regarding the transaction price of the financial product, and also responds to the fluctuation exceeding the predicted predetermined value. By performing a predetermined process such as stopping or interpolating the forecasting of the trading price of the commodity, the trading price of the financial instrument can be appropriately forecasted as needed.

[7. Other]
Although some of the embodiments of the present application have been described above in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the section of the description of the invention. It is possible to implement the invention in other improved forms.

  Further, among the processes described in the above embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be performed automatically by known methods.

  In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  In addition, the embodiments described above can be combined appropriately as long as the processing contents do not contradict each other.

  Also, the "section (module, unit)" described above can be read as "means" or "circuit" or the like. For example, the prediction unit can be read as prediction means or a prediction circuit.

Reference Signs List 1 information processing apparatus 2 transaction apparatus 3 terminal device 10 communication unit 20 storage unit 21 history information storage unit 22 learning information storage unit 23 detection information storage unit 24 prediction information storage unit 25 reception information storage unit 26 transaction information storage unit 30 control unit 31 Acquisition unit 32 Learning unit 33 Detection unit 34 Prediction unit 34a Second-order derivative value prediction unit 34b First-order derivative value prediction unit 34c Transaction price prediction unit 34d Price fluctuation prediction unit 34e Processing unit 34f Prediction stop unit 34g Prediction interpolation unit 35 Reception unit 36 Distribution Part 37 Transaction Processing Department N Network

Claims (7)

An acquisition unit that acquires history information on the transaction price of the financial instrument whose transaction price changes;
A second-order derivative value prediction unit that predicts a second-order derivative value regarding the time of the transaction price based on the information of the history acquired by the acquisition unit;
An information processing apparatus comprising: a transaction price prediction unit that predicts the transaction price based on the second-order derivative value predicted by the second-order derivative value prediction unit. It further comprises a first-order derivative value prediction unit that predicts a first-order derivative value regarding the time of the transaction price based on the information of the history acquired by the acquisition unit;
The transaction price prediction unit predicts the transaction price based on the second derivative value predicted by the second derivative value prediction unit and the first derivative value predicted by the first derivative value prediction unit. The information processing apparatus according to claim 1, characterized in that The history information includes information on the transaction price in a past fixed period,
The information processing according to claim 1 or 2, wherein the second-order derivative value predicting unit predicts a second-order derivative value regarding the time of the transaction price based on information regarding the transaction price in the past fixed period. apparatus. The information processing apparatus further comprises a detection unit that detects a change in the transaction price exceeding a predetermined value based on the information of the history acquired by the acquisition unit.
The second-order derivative value predicting unit predicts a second-order derivative value regarding the time of the transaction price based on information of the history excluding information accompanied by fluctuations exceeding the predetermined value detected by the detecting unit. The information processing apparatus according to any one of claims 1 to 3, wherein the information processing apparatus is characterized. A price fluctuation prediction unit that predicts fluctuation of the transaction price exceeding a predetermined value based on the information of the history acquired by the acquisition unit;
The information processing apparatus according to any one of claims 1 to 4, further comprising: a processing unit that executes a predetermined process according to a fluctuation exceeding the predetermined value predicted by the price fluctuation prediction unit. apparatus. An information processing method executed by a computer,
An acquisition step of acquiring history information on the transaction price of the financial instrument whose transaction price changes;
A second derivative value predicting step of predicting a second derivative value regarding the time of the transaction price based on the information of the history acquired in the acquiring step;
A transaction price prediction step of predicting the transaction price based on the second-order derivative value predicted in the second-order derivative value prediction step. An acquisition procedure for acquiring historical information on the transaction price of the financial instrument whose transaction price changes;
A second-order derivative value prediction procedure for predicting a second-order derivative value regarding the time of the transaction price based on the information of the history acquired in the acquisition procedure;
An information processing program causing a computer to execute a transaction price prediction procedure for predicting the transaction price based on the second order differential value predicted in the second order differential value prediction procedure.

Images