KR20230000411A - Server, method and computer program for providing investment guide - Google Patents

Abstract

A server for providing investment guides comprises: a collecting unit for collecting investment-related information on investment experts; a learning data generation unit for generating training data for a plurality of learning models based on the collected investment-related information; a learning unit for training a plurality of learning models based on the generated training data; an ensemble model generation unit for generating an investment simulation ensemble model for the investment experts based on the plurality of trained learning models; and an investment guide information provision unit for providing investment guide information to an investor terminal by using the investment simulation ensemble model. The plurality of learning models may include a stock price model, a finance model, and an economy model. Therefore, the server can help even individual investors with no investment knowledge to make investments similarly to the investment strategy of investment experts through the investment simulation ensemble model that has trained the investment style of the investment experts.

Description

Server, method and computer program providing investment guide {SERVER, METHOD AND COMPUTER PROGRAM FOR PROVIDING INVESTMENT GUIDE}

The present invention relates to a server, method and computer program for providing an investment guide.

As interest in financial technology increases, users who invest in 　 using investment products (eg, stocks, funds, etc.) are gradually increasing.

In the case of stock investment, high profits may occur depending on the ability to collect and analyze information, but losses may occur due to errors in judgment or market conditions.

Unlike investment institutions that specialize in investment, most individual investors who perform stock trading are finding it increasingly difficult to earn high returns due to lack of professional knowledge and information, lack of funds, etc.

On the other hand, the majority of individual investors want to follow the investment style (eg, trading technique, etc.) of an investment expert (eg, Warren Buffett, etc.). However, the trading techniques of investment experts are difficult to define with a small number of factors.

For example, although the investment expert's trading technique can be quantified to some extent through a rule-based model or a quantization model, loss of information may occur.

For example, it is possible to analyze profit and loss factors for each trading element of an investment expert through a portfolio analysis tool, but it is difficult to accurately derive the trading technique of an investment expert in an indirect way.

Korean Patent Publication No. 2013-0052043 (published on May 22, 2013)

The present invention is to solve the above-mentioned problems of the prior art, and learns a plurality of learning models based on investment-related information about investment experts, and provides investment guide information through an investment simulation ensemble model based on the learned plurality of learning models. want to provide

However, the technical problem to be achieved by the present embodiment is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, a server providing an investment guide according to a first aspect of the present invention includes a collection unit for collecting investment-related information about investment experts; a learning data generating unit generating learning data for a plurality of learning models based on the collected investment-related information; a learning unit for learning the plurality of learning models based on the generated learning data; an ensemble model generating unit generating an investment simulation ensemble model for the investment expert based on the learned plurality of learning models; and an investment guide information provider providing investment guide information to an investor terminal using the investment simulation ensemble model, wherein the plurality of learning models may include a stock price model, a financial model, and an economic model.

A method for providing an investment guide performed by an investment guide providing server according to a second aspect of the present invention includes the steps of collecting investment-related information for an investment expert; generating learning data for a plurality of learning models based on the collected investment-related information; learning the plurality of learning models based on the generated learning data; generating an investment simulation ensemble model for the investment expert based on the learned plurality of learning models; and providing investment guide information to an investor terminal using the investment simulation ensemble model, wherein the plurality of learning models may include a stock price model, a financial model, and an economic model.

A computer program stored in a computer readable recording medium containing a sequence of instructions for providing an investment guide according to the third aspect of the present invention, when executed by a computing device, collects investment-related information about investment experts, and collects the collected investment-related information. Based on investment-related information, generating learning data for a plurality of learning models, learning the plurality of learning models based on the generated learning data, and learning information about the investment expert based on the plurality of learned learning models. An investment simulation ensemble model may be generated, investment guide information may be provided to an investor terminal using the investment simulation ensemble model, and the plurality of learning models may include a sequence of instructions including a stock price model, a financial model, and an economic model. there is.

The above-described means for solving the problems is only illustrative and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the problem solving means of the present invention described above, the present invention learns a plurality of learning models based on investment-related information about investment experts, and invests through an investment simulation ensemble model based on the learned plurality of learning models. Guide information can be provided.

Through this, since the investment simulation ensemble model of the present invention provides judgments similar to those considered by investment experts when trading, even individual investors who do not have much investment knowledge can invest through the investment simulation ensemble model that has learned the investment style of investment experts. It can help you make investments similar to the investment strategy of experts.

1 is a block diagram of an investment guide providing server according to an embodiment of the present invention.
2a to 2b are diagrams for explaining a learning method of a plurality of learning models and a method of providing investment guide information using a plurality of learning models, according to an embodiment of the present invention.
3 is a flowchart illustrating a method of providing an investment guide according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. . In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

In this specification, a "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal or device may be performed instead by a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the corresponding server.

Hereinafter, specific details for the implementation of the present invention will be described with reference to the accompanying configuration diagram or process flow chart.

1 is a block diagram of an investment guide providing server 10 according to an embodiment of the present invention.

Referring to FIG. 1, the investment guide providing server 10 includes a collecting unit 100, a learning data generating unit 110, a learning unit 120, an ensemble model generating unit 130, and an investment guide information providing unit 140. and an ensemble model providing unit 150 . However, the investment guide providing server 10 shown in FIG. 1 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG. 1 .

The collection unit 100 may collect investment-related information for an investment expert (eg, a fund manager, etc.) from a securities company server.

Here, the investment-related information may include asset information on at least one investment item held by the investment expert, transaction details and transaction index information on the investment item held by the investment expert. Here, the asset information on at least one investment item may include holding weight information on the daily investment item.

For example, the collection unit 100 may collect first investment-related information about a first investment expert and collect first investment-related information about a second investment expert.

The learning data generation unit 110 may generate learning data for a plurality of learning models based on the collected investment-related information on investment experts. Here, the plurality of learning models may include a stock price model, a financial model, and an economic model.

The learning data generating unit 110 may generate learning data for a plurality of learning models for each investment expert based on investment-related information collected for each investment expert. For example, the learning data generation unit 110 uses the investment-related information of the first investment expert to learn a trading style for the first investment expert (eg, a trading position and holding ratio of investment items, etc.). Learning data for a learning model may be generated, and learning data for a plurality of learning models for learning a trading style for the second investment expert may be generated using the investment-related information of the second investment expert.

The learning data generation unit 110 may derive stock price-related index information from the collected investment-related information on investment experts, and generate first learning data for learning a stock price model based on the derived stock price-related index information. . Here, the index information related to the stock price may include, for example, stock price return, trading volume, stock price standard deviation, and stock price moving average (MV). Alternatively, stock price-related indicator information is, for example, 5-day yield (e.g., 10-day, 20-day, 60-day, 120-day yield), moving average line (MA5(20,60,120)) information, exponential moving average line (EMA5(20 ,60,120)) information, transaction volume information, OBV (On Balance Volume) information, PVT (Price Volume Trend) information, AD (Accumulation Distribution) information, separation degree information, RSI (Relative Strength Index) information, and the like may be further included.

The learning data generation unit 110 may derive financial-related ratio information from the collected investment-related information and generate second learning data for learning a financial model based on the derived financial-related ratio information. Here, financial-related ratio information includes, for example, Price Earning Ratio (PER), Return On Asset (ROA), Enterprise Value (EV), and Earnings Before Interest&Tex (EBITDA). , Depreciation and Amortization). In addition, financial ratio information, for example, ROE (Return On Equity) information, PBR (Price Book-value Ratio) information, PSR (Pice Sales Ratio) information, sales Profit rate information, net profit rate information, sales growth rate information, debt ratio information, dividend payout ratio information, and the like may be further included.

The learning data generation unit 110 may derive macroeconomic indicator-related information from the collected investment-related information, and generate third learning data for economic model learning based on the derived macroeconomic indicator-related information. Here, information related to macroeconomic indicators may include, for example, exchange rate information, oil price information, interest rate information, price information, raw material information, and GOD economic growth rate information.

The learning unit 120 may teach a trading style for an investment expert to a plurality of learning models based on the learning data for the investment expert.

For example, referring to FIG. 2A , the learning unit 120 inputs first learning data (data generated based on stock price-related index information) for a first investment expert into a stock price model 201 to model a stock price model ( 201), the stock price model 201 can be trained to predict the trading position information of the first investment expert and information on the holding ratio of investment items.

In addition, the learning unit 120 inputs second learning data (data generated based on financial-related ratio information) for the first investment expert into the financial model 203, and the first investment expert through the financial model 203. The financial model 203 may be trained to predict trading position information and holding ratio information of investment items.

In addition, the learning unit 120 inputs third learning data (data generated based on information related to macroeconomic indicators) for the first investment expert to the economic model 205 to determine the first investment through the economic model 205. The economic model 205 may be trained to predict the expert's trading position information and holding ratio information of investment items.

The ensemble model generation unit 130 may generate an investment simulation ensemble model for the investment expert based on the plurality of learned models.

For example, referring to FIG. 2B , the ensemble model generation unit 130 uses a stock price model 201, a financial model 203, and an economic model 205 in which the investment style of the first investment expert is learned to generate a first investment model. An investment simulation ensemble model 207 for investment experts may be generated.

The ensemble model generation unit 130 may set different weights to be assigned to each of the plurality of learning models based on the investment propensity of the investment expert. The investment characteristics of investment experts can be identified through the weights assigned to each learning model.

For example, if the weight of a stock price model is set higher than that of other learning models (financial model, economic model), it can be understood that investment experts make decisions on whether to invest while mainly checking stock price movements.

The ensemble model generation unit 130 may generate an investment simulation ensemble model that simulates the trading style of an investment expert based on a plurality of learning models and weights set for each of the plurality of learning models.

The ensemble model generation unit 130 may generate an investment simulating ensemble model that simulates a trading style of each investment expert for each of a plurality of investment experts.

Here, the investment simulation ensemble model can be expressed as [Equation 1].

[Equation 1]

Investment Simulation Ensemble Model = Stock Model* W1 + Financial Model* W2 + Economic Model* W3

If stock price data, financial data, and economic data at the current time are input into multiple learning models, the output values (trading position information and information on holdings of investment items) derived from each learning model will be used as input values for the investment simulation ensemble model. can

For example, referring to FIG. 2B, a first result of a multiplication operation between stock price data at the current time and a first weight set in the stock price model 201 is input to the investment simulation ensemble model 207, and the financial The second result of the multiplication operation between the second weights set in the data and financial model 203 is input to the investment simulation ensemble model 207, and the second result of the multiplication operation between the economic data and the third weights set in the economic model 205 3 results may be input to the investment simulation ensemble model 207 .

The investment simulation ensemble model 207 can derive final trading position information reflecting the investment style of the first investment expert and information on the holding ratio of the investment item based on the first result value, the second result value, and the third result value. there is.

The investment guide information providing unit 140 may provide investment guide information to an investor terminal using an investment simulation ensemble model. Here, the investment guide information is a guide that simulates an investment expert's investment in the transaction of an investment item, and may include information on the trading position of the investment item and holding ratio information of the investment item.

For example, the investment guide information provider 140 provides investment guide information (sell/sell) based on the final trading position information and holding ratio information derived from the investment simulation ensemble model 207 that simulates the trading style of the first investment expert. Guide information that suggests investment stocks with a high probability of buying and recommends the proportion of holdings in the investment stock) can be derived.

The ensemble model providing unit 150 may provide the investor terminal with a plurality of simulated investment ensemble models for a plurality of investment experts.

The investment guide information provider 140 may select at least one of a plurality of simulation ensemble models for investment from an investor terminal, and provide investment guide information to the terminal based on the selected simulation ensemble model for investment.

The investment guide information providing unit 140 inputs stock price data, financial data, and economic data at the current time to a plurality of learning models included in the investment simulation ensemble model selected by the investor terminal, and output values derived from each learning model are selected. An investment guide can be derived through the selected investment simulation ensemble model by using it as an input value of the investment simulation ensemble model.

When at least two or more investment simulation ensemble models are selected from the investor terminal, the investment guide information providing unit 140 transmits investment guide information for each selected two or more investment simulation ensemble models derived through each of the two or more selected investment simulation ensemble models to the investor terminal. can be provided to

When the trading position information for the investment item included in the investment guide information for each selected two or more investment simulation ensemble models conflicts with each other, the investment guide information providing unit 140 selects two or more investment simulation models using a softmax function. The probability for each ensemble can be calculated. Here, the softmax function is an activation function used in multi-class classification that classifies three or more classes. When there are N classes to be classified, an N-dimensional vector is input and the probability of belonging to each class is estimated. The output values of the Softmax function are all normalized values between 0 and 1, and the sum of the output values is always 1.

If the trading position information for the investment item included in the investment guide information for each selected two or more investment simulation ensemble models conflicts with each other, the investment guide information providing unit 140 selects an investment simulation ensemble with high probability from among the two or more selected investment simulation ensembles. The information derived from the investment guide may be provided to the investor terminal.

For example, when the first investment simulation ensemble model predicts buying with a probability of 0.5 and the second investment simulation ensemble model predicts selling with a probability of 0.7, the investment guide information provider 140 provides the first investment simulation ensemble model and a second investment simulation ensemble model that predicts the highest probability among the second investment simulation ensemble models may be selected, and investment guide information derived through the second investment simulation ensemble model may be provided to the investor terminal.

If the trading position information for the investment item included in the investment guide information for each of the selected two or more investment simulation ensemble models conflicts with each other, the investment guide information provider 140 selects the investor's preferred item among stock price items, financial items, and economic items. is selected from the investor terminal, an investment simulation ensemble is selected based on the selected items, and investment guide information derived through the selected investment simulation ensemble model may be provided to the investor terminal.

On the other hand, if you are skilled in the art, the collection unit 100, the learning data generation unit 110, the learning unit 120, the ensemble model generation unit 130, the investment guide information providing unit 140, and the ensemble model providing unit 150, respectively. It will be fully understood that these may be implemented separately, or one or more of them may be implemented in an integrated manner.

3 is a flowchart illustrating a method of providing an investment guide according to an embodiment of the present invention.

Referring to FIG. 3 , in step S301, the investment guide providing server 10 may collect investment-related information about an investment expert.

In step S303, the investment guide providing server 10 may generate learning data for a plurality of learning models based on the collected investment-related information. Here, the plurality of learning models may include a stock price model, a financial model, and an economic model.

In step S305, the investment guide providing server 10 may learn a plurality of learning models based on the generated learning data.

In step S307, the investment guide providing server 10 may generate an investment simulation ensemble model for investment experts based on a plurality of learned learning models.

In step S309, the investment guide providing server 10 may provide investment guide information to the investor terminal using the generated investment simulation ensemble model.

In the above description, steps S301 to S309 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

An embodiment of the present invention may be implemented in the form of a recording medium including instructions executable by a computer, such as program modules executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present invention. .

10: Server providing investment guide
100: collection unit
110: learning data generation unit
120: learning unit
130: ensemble model generation unit
140: investment guide information provision unit
150: ensemble model providing unit

Claims (20)

In a server that provides an investment guide,
a collection unit that collects investment-related information about investment professionals;
a learning data generating unit generating learning data for a plurality of learning models based on the collected investment-related information;
a learning unit for learning the plurality of learning models based on the generated learning data;
an ensemble model generating unit generating an investment simulation ensemble model for the investment expert based on the learned plurality of learning models; and
An investment guide information providing unit for providing investment guide information to an investor terminal using the investment simulation ensemble model.
including,
The plurality of learning models include a stock price model, a financial model and an economic model, the investment guide providing server.
According to claim 1,
The investment-related information includes asset information on at least one investment item held by the investment expert, transaction details on the investment item held, and transaction index information,
The asset information for the at least one investment item includes holding weight information for each investment item, the investment guide providing server.
According to claim 1,
The learning data generation unit derives stock price-related indicator information from the collected investment-related information, and generates first learning data for learning the stock price model based on the derived stock price-related indicator information;
The stock price-related index information includes stock price return, trading volume, stock price standard deviation and stock price moving average (MV, Moving Average), an investment guide providing server.
According to claim 1,
The learning data generator derives financial-related ratio information from the collected investment-related information, and generates second learning data for learning the financial model based on the derived financial-related ratio information;
The financial ratio information above includes Price Earning Ratio (PER), Return On Asset (ROA), Enterprise Value (EV), and Earnings Before Interest&Tex (EBITDA), Depreciation and Amortization (EBITDA). An investment guide providing server that includes inter-information.
According to claim 1,
The learning data generation unit derives macroeconomic indicator-related information from the collected investment-related information, and generates third learning data for learning the economic model based on the derived macroeconomic indicator-related information,
The information related to macroeconomic indicators includes exchange rate information, oil price information, interest rate information, price information, and GOD economic growth rate information, an investment guide providing server.
According to claim 1,
The ensemble model generating unit
Generating the investment simulation ensemble model based on the plurality of learning models and weights set for each of the plurality of learning models,
When stock price data, financial data, and economic data at the current time are input to the plurality of learning models, the output value derived from each learning model is used as an input value of the investment simulation ensemble model. Investment guide providing server.
According to claim 1,
An ensemble model providing unit for providing a plurality of simulated investment ensemble models for a plurality of investment experts to the investor terminal.
To further include, the investment guide providing server.
According to claim 7,
The investment guide information provider
An investment guide providing server that receives at least one of the plurality of investment simulation ensemble models selected from the investor terminal and provides the investment guide information to the investor terminal based on the selected investment simulation ensemble model.
According to claim 8,
The investment guide information provider
Enter stock price data, financial data and economic data at the current time into a plurality of learning models included in the investment simulation ensemble model selected by the investor terminal;
Deriving the investment guide information through the selected investment simulation ensemble model by using the output value derived from each learning model as an input value of the selected investment simulation ensemble model;
The investment guide information includes trading position information for the investment item and holding ratio information of the investment item, the investment guide providing server.
According to claim 8,
When at least two or more investment simulation ensemble models are selected from the investor terminal,
The investment guide providing server, wherein the investment guide information providing unit provides investment guide information for each of the selected two or more investment simulation ensemble models derived through each of the selected two or more investment simulation ensemble models.
According to claim 10,
If the trading position information for the investment item included in the investment guide information for each of the two or more selected investment simulation ensemble models conflicts,
The investment guide information providing unit provides investment guide information derived through an investment simulation ensemble with a high probability among the selected two or more investment simulation ensembles to the investor terminal.
In the method of providing an investment guide performed by the investment guide providing server,
Collecting investment-related information about investment professionals;
generating learning data for a plurality of learning models based on the collected investment-related information;
learning the plurality of learning models based on the generated learning data;
generating an investment simulation ensemble model for the investment expert based on the learned plurality of learning models; and
Providing investment guide information to an investor terminal using the investment simulation ensemble model
including,
Wherein the plurality of learning models include a stock price model, a financial model and an economic model.
According to claim 12,
The step of generating learning data for the plurality of learning models
Deriving macroeconomic indicator-related information from the collected investment-related information; and
Generating third learning data for learning the economic model based on the derived macroeconomic indicator-related information;
Wherein the information related to macroeconomic indicators includes exchange rate information, oil price information, interest rate information, price information, and GOD economic growth rate information.
According to claim 12,
The step of generating an investment simulation ensemble model for the investment expert
Generating the investment simulation ensemble model based on the plurality of learning models and weights set for each of the plurality of learning models;
When the stock price data, financial data and economic data at the current time are input to the plurality of learning models, the output value derived from each learning model is used as an input value of the investment simulation ensemble model. How to provide an investment guide.
According to claim 12,
Further comprising the step of providing a plurality of simulated investment ensemble models for a plurality of investment experts to the investor terminal, the investment guide providing method.
According to claim 15,
The step of providing investment guide information to the investor terminal
Receiving a selection of at least one of the plurality of investment simulation ensemble models from the investor terminal; and
And providing the investment guide information to the investor terminal based on the selected investment simulation ensemble model.
17. The method of claim 16,
The step of providing investment guide information to the investor terminal
Inputting current stock price data, financial data, and economic data into a plurality of learning models included in the investment simulation ensemble model selected by the investor terminal; and
Deriving the investment guide information through the selected investment simulation ensemble model by using an output value derived from each learning model as an input value of the selected investment simulation ensemble model;
The method of providing an investment guide, wherein the investment guide information includes trading position information for an investment item and information on a holding ratio of the investment item.
17. The method of claim 16,
The step of providing investment guide information to the investor terminal
When at least two or more investment simulation ensemble models are selected from the investor terminal, providing investment guide information for each of the selected two or more investment simulation ensemble models derived through each of the selected two or more investment simulation ensemble models. , how to provide an investment guide.
17. The method of claim 16,
The step of providing investment guide information to the investor terminal
If the trading position information for the investment item included in the investment guide information for each selected two or more investment simulation ensemble models conflicts, the investment guide information derived through the investment simulation ensemble with high probability among the selected two or more investment simulation ensembles To include the step of providing to the investor terminal, an investment guide providing method.
A computer program stored on a computer readable recording medium comprising a sequence of instructions for providing an investment guide,
When the computer program is executed by a computing device,
Collect investment-related information for investment professionals;
Generate learning data for a plurality of learning models based on the collected investment-related information;
Learning the plurality of learning models based on the generated learning data;
Generating an investment simulation ensemble model for the investment expert based on the plurality of learned models;
Providing investment guide information to an investor terminal using the investment simulation ensemble model;
The plurality of learning models include a sequence of instructions including a stock price model, a financial model and an economic model, a computer program stored on a computer readable recording medium.

Images