Financial investment risk control system based on big data technology

Abstract

The invention relates to the technical field of investment risk control, in particular to a financial investment risk control system based on a big data technology, which comprises a stock transaction data receiving module, a risk reminding module, a stock risk control reminding module and a threshold optimization module. The risk reminding module analyzes a psychological tolerance threshold value when the user sells the stock according to the transaction price when the user buys and sells the stock, rejects transaction data influencing the analysis of the psychological tolerance threshold value in the stock transaction process in the process, and outputs a risk reminding signal to the user when the stock price does not conform to the psychological tolerance threshold value; therefore, the user can alert the stock price reduction information in advance, the situation that the user misses the best loss stopping opportunity due to emotion panic or information negligence is avoided, and then the stock risk control reminding module analyzes whether the user carries out risk operation or not when the stock price is reduced according to the number of times of stock transaction of the user.

Description

Technical Field

[0001] The present invention relates to the field of investment risk control technology, and in particular to a financial investment risk control system based on big data technology. Background Art

[0002] Financial investment includes a variety of forms such as stock investment. Investors enter the market with the goal of making profits by purchasing stocks. Given that different investors have significant differences in investment ability, experience, risk preference, and market understanding and judgment, their investment decision-making process mainly determines the timing of buying or selling based on the fluctuations of stock prices.

[0003] Usually, when the stock price falls to the psychological price set by the investor's personal expectations and risk tolerance, they will consider selling the stock to stop loss or lock in profit; on the contrary, when the stock price is on the rise, it may attract investors to buy. However, under the current technical framework, since each investor's psychological price is highly personalized and in dynamic change, it is difficult for existing technology to accurately analyze and determine the specific price point at which investors will choose to sell stocks. Therefore, investors need to continue to pay close attention to stock price trends and be ready to make a judgment on whether to execute a sell operation at any time, which requires users to invest a lot of time and energy. In view of this, we propose a financial investment risk control system based on big data technology. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that it is impossible to analyze the specific price point at which a user sells stocks.

[0005] To achieve the above-mentioned purpose, the present invention provides a financial investment risk control system based on big data technology, including a stock transaction data receiving module, a risk reminder module, a stock risk control reminder module and a threshold optimization module;

[0006] The stock transaction data receiving module is used to obtain transaction records and obtain current stock prices through a web crawler;

[0007] The risk reminder module regards the transaction record of the day as the current transaction record and all previous transaction records as historical transaction records, calculates the average of the price difference in historical transactions, and defines it as the large transaction threshold;

[0008] Retrieve the selling price and the stock price at the previous moment corresponding to the price difference less than the large transaction threshold in historical transactions, calculate the average of the price difference between the current selling price and the stock price at the previous moment, and define it as the user's psychological tolerance threshold;

[0009] Sense the current trading signal, if the current stock price is less than the stock price at the previous moment, or the price difference between the current stock price and the stock price at the previous moment is greater than the psychological tolerance threshold, output a risk warning signal;

[0010] The stock risk control reminder module is used to calculate the number of stock transactions at different time nodes in the historical transaction records. After the risk reminder module outputs a risk warning signal, if the number of transactions at the current time node is greater than the number of historical stock transactions, a risk control reminder signal is output;

[0011] The threshold optimization module is used to analyze the user's transaction type according to the number of stock transactions and the price difference in historical transactions, and adjust the user's psychological tolerance threshold in the risk reminder module according to the transaction type.

[0012] As a further improvement of the technical solution, the steps of the stock transaction data receiving module obtaining the transaction record are as follows:

[0013] Calling an API function that matches the stock database server protocol format to send the authentication token to the stock database server;

[0014] After receiving the authentication token, the stock database server compares the authentication token according to its own verification mechanism;

[0015] When the verification mechanism = authentication token, the stock database server sends a connection success response to the heterogeneous data source extraction module stock transaction data receiving module, and the connection is established successfully;

[0016] When the verification mechanism ≠ authentication token, the connection establishment fails;

[0017] When the connection is successful, the transaction records in the stock database server are extracted through the established connection.

[0018] As a further improvement of the technical solution, the steps of the stock transaction data receiving module obtaining the current stock price through a web crawler are as follows:

[0019] The web crawler uses the HTTP protocol to send a request to the website that stores the current stock price, notifying that it needs to obtain the current stock price;

[0020] After receiving the request, the website storing the current stock price returns a response indicating that the request is successful or failed. If the request fails, the web crawler continues to send requests to different websites storing the current stock price until the request succeeds.

[0021] When the request succeeds, the current stock price is obtained.

[0022] As a further improvement of the technical solution, the steps of defining the large transaction threshold in the risk reminder module are as follows:

[0023] Retrieve several stock selling prices and last moment prices in the historical transaction records in the stock transaction data receiving module, select the transaction records corresponding to the selling price < last moment price, and calculate the price difference in sequence: ;

[0024] in, is the price difference, represents the price difference quantity, For the selling price, is the price at the previous moment;

[0025] Compute the mean of several price differences: ,in The threshold for large transactions.

[0026] As a further improvement of the technical solution, the steps of defining the user's psychological tolerance threshold in the risk reminder module are as follows:

[0027] Calculated price difference < large transaction threshold The corresponding mean is: ;

[0028] in, The psychological tolerance threshold of the user is defined. The price difference is less than the large transaction threshold The corresponding price difference is is the price difference quantity.

[0029] As a further improvement of the technical solution, the steps of outputting the risk control reminder signal by the stock risk control reminder module are as follows:

[0030] Perceive the number of transactions corresponding to historical transaction records per day: ;

[0031] Calculate the average number of transactions per day: ,in for The total number of transactions corresponding to the number of days, is the number of historical trading days;

[0032] Perceive the risk warning signal output by the risk warning module, the number of transactions on the day is less than , output risk control reminder signal.

[0033] As a further improvement of the technical solution, the steps of analyzing the user transaction type by the threshold optimization module are as follows:

[0034] Calculate the median of the average number of transactions , calculate the median of the user's psychological tolerance threshold in the risk reminder module, ;

[0035] The number of transactions per day and Compare the price difference between the current stock price and the previous stock price and contrast;

[0036] Record transaction times> and number of transactions The number of times and , record the price difference> and price difference< The number of and ;

[0037] like > , < , then the user type is determined to be a high-frequency small-amount transaction type;

[0038] like < , > , then the user type is determined to be a low-frequency large-amount transaction type;

[0039] like < , > , then the user type is determined to be a low-frequency small-amount transaction type;

[0040] like > , > , then the user type is determined to be a high-frequency large-value transaction type.

[0041] As a further improvement of the technical solution, the steps of adjusting the user's psychological tolerance threshold by the threshold optimization module are as follows:

[0042] Perceived user transaction types: high-frequency small-amount transaction type, low-frequency large-amount transaction type, low-frequency small-amount transaction type, and high-frequency large-amount transaction type;

[0043] The adjusted psychological tolerance threshold for high-frequency small-amount transaction users: ;

[0044] The adjusted psychological tolerance threshold for low-frequency and large-value transaction users: ;

[0045] The adjusted psychological tolerance threshold for low-frequency small-amount transaction users: ;

[0046] The adjusted psychological tolerance threshold for high-frequency and large-value transaction users: ;

[0047] in, The user psychological tolerance threshold set for the risk reminder module, are the adjustment ratios, and , .

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] In this financial investment risk control system based on big data technology, the risk reminder module analyzes the psychological tolerance threshold of users when selling stocks based on the transaction prices of users when buying and selling stocks, and in this process eliminates the transaction data that affects the psychological tolerance threshold during the stock trading process. When the stock price does not meet the psychological tolerance threshold, a risk warning signal is output to the user, so that the user can be alerted to the stock price reduction information in advance, avoiding missing the best stop loss opportunity due to emotional panic or information negligence;

[0050] Then, the stock risk control reminder module analyzes whether the user performs risky operations when the stock price drops based on the number of times the user trades stocks. Frequent transactions in a short period of time and continuous increase in positions when the stock price continues to fall are high-risk operations. Therefore, when the user performs risky operations, the risk control reminder signal is output to the employee in time to prevent the user from causing greater losses.

[0051] Then, the threshold optimization module analyzes the user transaction type based on the number of stock transactions in the stock risk control reminder module and the transaction price when buying and selling stocks in the risk reminder module, and further optimizes the user's psychological tolerance threshold in the risk reminder module based on the user's transaction type. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is the overall module principle diagram of the present invention.

[0053] The meaning of each number in the figure is:

[0054] 100. Stock transaction data receiving module; 200. Risk reminder module; 300. Stock risk control reminder module; 400. Threshold optimization module. DETAILED DESCRIPTION

[0055] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] like Figure 1 As shown, the financial investment risk control system based on big data technology includes a stock transaction data receiving module 100, a risk reminder module 200, a stock risk control reminder module 300 and a threshold optimization module 400;

[0057] The terms used in the exemplary embodiments shown in the drawings are not intended to limit the present invention. In the drawings, the same units / elements are given the same reference numerals.

[0058] Unless otherwise determined, the terms used herein, including technical terms, have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0059] The following are some definitions of terms:

[0060] Transaction records include: stock buying price, selling price, buying time, selling time, stock shares and historical stock prices;

[0061] The stock transaction data receiving module 100 is used to obtain transaction records and obtain current stock prices through a web crawler;

[0062] The steps for the stock transaction data receiving module 100 to obtain transaction records are as follows:

[0063] Calling an API function that matches the stock database server protocol format to send the authentication token to the stock database server;

[0064] After receiving the authentication token, the stock database server compares the authentication token according to its own verification mechanism;

[0065] When the verification mechanism = authentication token, the stock database server sends a connection success response to the heterogeneous data source extraction module stock transaction data receiving module 100, and the connection is established successfully;

[0066] When the verification mechanism ≠ authentication token, the connection establishment fails;

[0067] When the connection is successful, the transaction records in the stock database server are extracted through the established connection.

[0068] The steps for the stock transaction data receiving module 100 to obtain the current stock price through a web crawler are as follows:

[0069] The web crawler uses the HTTP protocol to send a request to the website that stores the current stock price, notifying that it needs to obtain the current stock price;

[0070] After receiving the request, the website storing the current stock price returns a response indicating that the request is successful or failed. If the request fails, the web crawler continues to send requests to different websites storing the current stock price until the request succeeds.

[0071] When the request succeeds, the current stock price is obtained.

[0072] The present invention fully considers that in the stock trading scenario, the user's trading decision is often closely related to his psychological tolerance. If the stock price shows a downward trend, some users tend to sell their stocks immediately, indicating that the psychological tolerance of such users is relatively weak. However, in the process of stock trading, when the user cannot pay attention to the real-time stock market in time due to various reasons, the final selling price of the stock will be lower than the bottom line of his original psychological expectation, thereby causing unnecessary losses. Therefore, the risk reminder module 200 regards the transaction record of the day as the current transaction record, and all previous transaction records as historical transaction records;

[0073] Calculate the average of the price differences in historical transactions and define it as the large transaction threshold;

[0074] The present invention further considers that in the process of setting the psychological tolerance threshold by the risk reminder module 200, users may sometimes have a fluke mentality and expect the stock price to rise, thus delaying the decision to sell. If the stock price cannot rise, the user will sell in large amounts. If the impact of such large transactions cannot be eliminated before setting the psychological tolerance threshold, the psychological tolerance threshold will be set inaccurately. Therefore, the selling price and the stock price at the previous moment corresponding to the price difference in historical transactions < the large transaction threshold are first retrieved, and the average of the price difference corresponding to the selling price at this time and the stock price at the previous moment is calculated again, and defined as the user's psychological tolerance threshold;

[0075] Sense the current trading signal, if the current stock price is less than the stock price at the previous moment, or the price difference between the current stock price and the stock price at the previous moment is greater than the psychological tolerance threshold, output a risk warning signal;

[0076] The steps for the risk reminder module 200 to define the large transaction threshold are as follows:

[0077] Retrieve several stock selling prices and last moment prices in the historical transaction records in the stock transaction data receiving module 100, select the transaction records corresponding to the selling price < last moment price, and calculate the price difference in sequence: ;

[0078] in, is the price difference, represents the price difference quantity, For the selling price, is the price at the previous moment;

[0079] Compute the mean of several price differences: ,in The threshold for large transactions.

[0080] The steps of the risk reminder module 200 to define the user's psychological tolerance threshold are as follows:

[0081] Calculated price difference < large transaction threshold The corresponding mean is: ;

[0082] in, The psychological tolerance threshold of the user is defined. The price difference is less than the large transaction threshold The corresponding price difference is is the price difference quantity.

[0083] The present invention also fully considers that when the risk reminder module 200 outputs a risk warning signal, it means that the fluctuation of the current stock trading price has exceeded the user's preset psychological tolerance threshold. However, when the stock price falls and causes a book loss, the user will try his best to avoid confirming the loss due to loss aversion. He would rather take the risk of continuing to increase his position, hoping to lower the average cost and wait for the stock price to rise to achieve a break-even or even profit, rather than stop loss in time. Therefore, if the user is not reminded in time during this process, greater losses may be caused. Therefore, the stock risk control reminder module 300 calculates the number of stock transactions at different time nodes in the historical transaction records. After the risk reminder module 200 outputs a risk warning signal, if the number of transactions at the current time node is greater than the number of historical stock transactions, a risk control reminder signal is output.

[0084] The steps for the stock risk control reminder module 300 to output the risk control reminder signal are as follows:

[0085] Perceive the number of transactions corresponding to historical transaction records per day: ;

[0086] Calculate the average number of transactions per day: ,in for The total number of transactions corresponding to the number of days, is the number of historical trading days;

[0087] The risk warning signal output by the risk sensing warning module 200 is the number of transactions per day < , output risk control reminder signal.

[0088] The present invention further takes into account that in the process of the risk reminder module 200 setting the psychological tolerance threshold based on historical transaction records, as the stock trading time continues to extend, the amount of historical transaction data will continue to expand. In this case, if the user wants to avoid the risk of declining returns in stock trading, he will adopt different trading frequency strategies to deal with it. If the psychological tolerance threshold cannot be dynamically adjusted according to changes in user trading behavior at this time, it will cause investors to fall into unnecessary losses when making stock trading decisions due to incorrect risk warnings or missing warnings, causing serious damage to their investment benefits and endangering the stability and sustainability of asset security. Therefore, the threshold optimization module 400 analyzes the user's transaction type according to the number of stock transactions and the price difference in historical transactions, and adjusts the user's psychological tolerance threshold in the risk reminder module 200 according to the transaction type.

[0089] The steps of the threshold optimization module 400 to analyze the user transaction type are as follows:

[0090] Calculate the median of the average number of transactions , calculate the median of the user's psychological tolerance threshold in the risk reminder module 200, ;

[0091] The median indicates the approximate level of the user's transaction frequency and the user's psychological tolerance threshold. By dividing the transaction frequency and the user's psychological tolerance threshold into upper and lower parts, by comparing with the median, it is possible to intuitively determine whether the current transaction situation is higher or lower than this middle level, and then analyze the position of the user's transaction behavior in the overall transaction frequency and user psychological tolerance threshold distribution;

[0092] The number of transactions per day and Compare the price difference between the current stock price and the previous stock price and contrast;

[0093] Record transaction times> and number of transactions The number of times and , record the price difference> and price difference< The number of and ;

[0094] like > , < , then it is determined that the user has a high number of stock transactions, but the price fluctuation range corresponding to the amount of each transaction is small, and the user type is determined to be a high-frequency small-amount transaction type;

[0095] like < , > , then it is determined that the number of stock transactions by the user is low, but the stock price fluctuations involved in each transaction are large, then the user type is determined to be a low-frequency large-amount transaction type;

[0096] like < , > , then it is determined that the number of stock transactions by the user is low, but the stock price involved in each transaction fluctuates greatly, then the user type is determined to be a low-frequency small-amount transaction type;

[0097] like > , > , then it is determined that the user has a high number of stock transactions, but the stock price fluctuations involved in each transaction are large, then the user type is determined to be a high-frequency large-amount transaction type.

[0098] The steps of the threshold optimization module 400 to adjust the user's psychological tolerance threshold are as follows:

[0099] Perceived user transaction types: high-frequency small-amount transaction type, low-frequency large-amount transaction type, low-frequency small-amount transaction type, and high-frequency large-amount transaction type;

[0100] The adjusted psychological tolerance threshold for high-frequency small-amount transaction users: ;

[0101] The adjusted psychological tolerance threshold for low-frequency and large-value transaction users: ;

[0102] The adjusted psychological tolerance threshold for low-frequency small-amount transaction users: ;

[0103] The adjusted psychological tolerance threshold for high-frequency and large-value transaction users: ;

[0104] in, The user psychological tolerance threshold set for the risk reminder module 200, are the adjustment ratios, and , ;

[0105] Although high-frequency small-amount transaction type users trade frequently, they are sensitive to smaller price fluctuations. "Sensitive" means that the price fluctuation range that users are accustomed to is relatively small. When deciding to appropriately increase their psychological tolerance threshold, it is considered to reduce unnecessary risk warnings caused by frequent small fluctuations. The adjustment range is relatively limited. High-frequency large-amount transaction type users not only trade frequently, but can also withstand larger price fluctuations. Their tolerance for price fluctuations is inherently strong. Therefore, when adjusting the psychological tolerance threshold ;

[0106] Low-frequency, large-amount transaction type users have few transactions and are very sensitive to price fluctuations. They wait for relatively large price fluctuations to occur before trading. Therefore, in order to be able to more keenly capture price fluctuations that may affect trading decisions, the psychological tolerance threshold is appropriately lowered. Low-frequency, small-amount transaction type users have few transactions and large price fluctuations in each transaction, but they have a low tolerance for price fluctuations. Therefore, the psychological tolerance threshold also needs to be lowered. However, low-frequency, small-amount transaction type users do not need to significantly lower the threshold to capture risk signals like low-frequency, large-amount transaction type users. Therefore .

[0107] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A financial investment risk control system based on big data technology, characterized by: It comprises a stock trading data receiving module (100), a risk reminder module (200), a stock risk control reminder module (300) and a threshold optimization module (400); The stock transaction data receiving module (100) is used to obtain transaction records and obtain current stock prices through a web crawler; The risk warning module (200) regards the transaction record of the day as the current transaction record and all previous transaction records as the historical transaction records, calculates the average of the price difference in the historical transactions, and defines it as the large transaction threshold; Retrieve the selling price and the stock price at the previous moment corresponding to the price difference less than the large transaction threshold in historical transactions, calculate the average of the price difference between the current selling price and the stock price at the previous moment, and define it as the user's psychological tolerance threshold; Sense the current trading signal, if the current stock price is less than the stock price at the previous moment, or the price difference between the current stock price and the stock price at the previous moment is greater than the psychological tolerance threshold, output a risk warning signal; The stock risk control reminder module (300) is used to calculate the number of stock transactions at different time nodes in the historical transaction records. After the risk reminder module (200) outputs a risk reminder signal, if the number of transactions at the current time node is greater than the number of historical stock transactions, then a risk control reminder signal is output; The threshold optimization module (400) is used to analyze the user's transaction type according to the number of stock transactions and the price difference in historical transactions, and adjust the user's psychological tolerance threshold in the risk reminder module (200) according to the transaction type.

2. The financial investment risk control system based on big data technology according to claim 1 is characterized by: The steps of the stock transaction data receiving module (100) acquiring transaction records are as follows: Calling an API function that matches the stock database server protocol format to send the authentication token to the stock database server; After receiving the authentication token, the stock database server compares the authentication token according to its own verification mechanism; When the verification mechanism = authentication token, the stock database server sends a connection success response to the heterogeneous data source extraction module stock transaction data receiving module (100), and the connection is established successfully; When the verification mechanism ≠ authentication token, the connection establishment fails; When the connection is successful, the transaction records in the stock database server are extracted through the established connection.

3. The financial investment risk control system based on big data technology according to claim 1 is characterized by: The steps of the stock transaction data receiving module (100) obtaining the current stock price through a web crawler are as follows: The web crawler uses the HTTP protocol to send a request to the website that stores the current stock price, notifying that it needs to obtain the current stock price; After receiving the request, the website storing the current stock price returns a response indicating that the request is successful or failed. If the request fails, the web crawler continues to send requests to different websites storing the current stock price until the request succeeds. When the request succeeds, the current stock price is obtained.

4. The financial investment risk control system based on big data technology according to claim 3 is characterized by: The steps of defining the large transaction threshold in the risk reminder module (200) are as follows: Retrieving a number of stock selling prices and prices at the last moment in the historical transaction records in the stock transaction data receiving module (100), selecting the transaction records corresponding to the selling price < the price at the last moment, and calculating the price differences in sequence: ; in, is the price difference, represents the price difference quantity, For the selling price, is the price at the previous moment; Compute the mean of several price differences: ,in The threshold for large transactions.

5. The financial investment risk control system based on big data technology according to claim 4 is characterized by: The steps of defining the user's psychological tolerance threshold in the risk reminder module (200) are as follows: Calculated price difference < large transaction threshold The corresponding mean is: ; in, The psychological tolerance threshold of the user is defined. The price difference is less than the large transaction threshold The corresponding price difference is is the price difference quantity.

6. The financial investment risk control system based on big data technology according to claim 1 is characterized by: The steps of outputting the risk control reminder signal by the stock risk control reminder module (300) are as follows: Perceive the number of transactions corresponding to historical transaction records per day: ; Calculate the average number of transactions per day: ,in for The total number of transactions corresponding to the number of days, is the number of historical trading days; The risk warning signal output by the risk warning module (200) is sensed, and the number of transactions on the day is less than , output risk control reminder signal.

7. The financial investment risk control system based on big data technology according to claim 5 is characterized by: The steps of analyzing the user transaction type by the threshold optimization module (400) are as follows: Calculate the median of the average number of transactions , calculating the median of the user's psychological tolerance threshold in the risk reminder module (200), ; The number of transactions per day and Compare the price difference between the current stock price and the previous stock price and contrast; Record transaction times> and number of transactions The number of times and , record the price difference> and price difference< The number of and ; like > , < , then the user type is determined to be a high-frequency small-amount transaction type; like < , > , then the user type is determined to be a low-frequency large-amount transaction type; like < , > , then the user type is determined to be a low-frequency small-amount transaction type; like > , > , then the user type is determined to be a high-frequency large-value transaction type.

8. The financial investment risk control system based on big data technology according to claim 7 is characterized by: The steps of the threshold optimization module (400) adjusting the user's psychological tolerance threshold are as follows: Perceived user transaction types: high-frequency small-amount transaction type, low-frequency large-amount transaction type, low-frequency small-amount transaction type, and high-frequency large-amount transaction type; The adjusted psychological tolerance threshold for high-frequency small-amount transaction users: ; The adjusted psychological tolerance threshold for low-frequency and large-value transaction users: ; The adjusted psychological tolerance threshold for low-frequency small-amount transaction users: ; The adjusted psychological tolerance threshold for high-frequency and large-value transaction users: ; in, a user psychological tolerance threshold set for the risk reminder module (200), are the adjustment ratios, and , .

Images