An intelligent risk control method and system based on financial derivative transactions

Abstract

This invention discloses an intelligent risk control method and system based on financial derivatives trading, belonging to the field of intelligent risk management technology. By uniformly capturing and processing internal and external information, aligned and real-time integrated financial derivatives trading data is obtained. Through the fusion of financial derivatives trading risk prediction models and risk control rules, the accuracy of real-time risk indicator predictions for financial derivatives trading is significantly improved. Based on these predictions, real-time and accurate real-time hedging strategies for financial derivatives trading are generated to achieve dynamic adjustment of the hedging strategies. Corresponding real-time risk control tools are selected for corresponding transaction execution, achieving efficient risk control management of the trading process and improving the reliability of financial derivatives trading management.

Description

Technical Field

[0001] This invention belongs to the field of intelligent risk control management technology, specifically relating to an intelligent risk control method and system based on financial derivatives trading. Background Technology

[0002] In the field of financial derivatives trading, effective risk management is the core guarantee for the sound operation of enterprises. With the increasing complexity and volatility of global financial markets, risk management in financial derivatives trading faces unprecedented challenges. Currently, the risk management methods and technologies commonly used in the industry have several significant shortcomings, making it difficult to meet the real-time, accurate, and systematic requirements of modern financial trading.

[0003] First, existing risk management systems commonly suffer from data silos and processing delays. Transaction data, market information, financial data, and risk indicators are scattered across multiple independent systems, with heterogeneous data formats and synchronization lags, leading to significant delays in risk identification and decision-making. Traditional batch processing architectures typically only provide risk analysis reports the following day, failing to meet real-time risk control needs. Existing technical solutions often rely on statistical models or fixed rules based on historical data, such as traditional VaR calculation methods, which struggle to dynamically reflect market structure changes and cannot predict extreme risk events in a timely manner. Risk analysis results often require manual interpretation and strategy development, resulting in a slow response process and hindering real-time early warning and intervention. Second, existing hedging strategies largely rely on fixed hedging ratios or empirical rules, failing to consider real-time changes in market risk and liquidity, leading to insufficient hedging or excessive costs, increasing liquidity risk and funding costs.

[0004] As mentioned above, how to provide an intelligent risk control method and system based on financial derivatives trading that can achieve real-time data fusion, accurate risk prediction, intelligent strategy execution, and multi-tool linkage management has become an urgent problem to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent risk control method and system based on financial derivatives trading, in order to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides an intelligent risk control method based on financial derivatives trading, comprising: Acquire historical financial derivatives trading data and real-time financial derivatives pending trading data, wherein each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information; Based on the historical financial derivatives trading data, a financial derivatives trading risk prediction model is trained, and the real-time financial derivatives trading data is used as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. Based on the real-time financial derivatives pending trading data and the predicted real-time risk indicators for financial derivatives trading, a corresponding real-time financial derivatives trading strategy is generated, wherein the real-time financial derivatives trading strategy includes a real-time financial derivatives hedging strategy. Based on the real-time trading strategy for the financial derivatives, the corresponding trading management tool is invoked as a real-time risk control tool to execute the real-time trading strategy for the financial derivatives and complete the transaction.

[0007] In one possible design, historical financial derivatives trading data and real-time financial derivatives pending trading data are acquired, including: Through the enterprise financial management database, obtain historical transaction records, historical risk event records, historical fund flow records, and historical credit limit usage records corresponding to each completed financial derivative transaction. Based on the historical transaction records, obtain historical external market data, historical transaction regulatory data, and historical counterparty credit data corresponding to each historical transaction record through external API interfaces. By using the corporate financial management database, we can obtain real-time cash flow data for each financial derivative product to be traded, and obtain real-time external market data, real-time transaction supervision data, and real-time counterparty credit data through external API interfaces. For each completed financial derivative transaction, the corresponding historical transaction records, historical risk event records, historical fund flow records, historical quota usage records, historical external market data, historical transaction regulatory data, and historical counterparty credit data are integrated into the original historical financial derivative transaction data. The original historical financial derivative transaction data is then cleaned and standardized to obtain the historical financial derivative transaction data. For each financial derivative to be traded, the corresponding real-time fund flow data, real-time external market data, real-time transaction supervision data, and real-time counterparty credit data are integrated into the original real-time financial derivative to be traded data. The original real-time financial derivative to be traded data is then cleaned and standardized to obtain the pre-real-time financial derivative to be traded data. Obtain preset transaction limit approval criteria, and use the transaction limit approval criteria to approve the real-time fund flow data in the pre-real-time financial derivatives pending transaction data, so as to use the pre-real-time financial derivatives pending transaction data that has passed the limit approval as the real-time financial derivatives pending transaction data.

[0008] In one possible design, a financial derivatives trading risk prediction model is trained based on the aforementioned historical financial derivatives trading data, including: The corresponding historical fund flow records and historical quota usage records are extracted from the historical financial derivatives transaction data as training data, wherein the training data uses the historical fund flow records as the target independent variable and the historical quota usage records as the target response variable. Mean squared error is selected as the loss function, and the arithmetic mean of each target response variable in the training data is calculated to obtain the average value of the target response variable; Obtain a preset decision tree model structure, establish an initial decision tree based on the decision tree model structure, take the average value of the target response variable corresponding to each target independent variable in the training data as the initial target prediction value of the initial decision tree, and calculate the corresponding initial decision tree residual based on the difference between the initial target prediction value and the target response variable corresponding to each target independent variable. Based on the decision tree model structure, an updated decision tree is established. The updated decision tree is used to fit the residual of the initial decision tree of the initial decision tree. The updated decision tree and the initial decision tree after the residual fitting are summed to obtain the current decision tree. With the goal of minimizing the loss function, the current decision tree is updated multiple times based on the training data to obtain a financial derivatives trading risk prediction model.

[0009] In one possible design, with the goal of minimizing the loss function, the current decision tree is updated multiple times based on the training data to obtain a financial derivatives trading risk prediction model, including: The current decision tree is used to predict each of the target independent variables in the training data, and the predicted output values ​​of multiple leaf nodes of the current decision tree are obtained. The mean of the predicted output values ​​of each leaf node is calculated as the current decision tree prediction value. Based on the current decision tree prediction value, the negative gradient of each target response variable is calculated using the following formula (1) to obtain the current decision tree residual value corresponding to each target independent variable: (1) in, For each of the aforementioned target independent variables index number, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree prediction value, Represent each of the stated target independent variables The corresponding target response variable, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree predictions and each of the stated target independent variables The corresponding loss function values ​​between the target response variables, This indicates the current decision tree's response to each of the stated objective variables. The residual value difference; For the current decision tree, the updated decision tree is used to learn the current decision tree's understanding of each of the target independent variables. The residual difference is learned, and the corresponding current update decision tree is trained using the training data with the goal of minimizing the loss function. Obtain a preset decision tree learning rate, use the decision tree learning rate to perform weighted processing on the current updated decision tree, and sum the current updated decision tree after weighted processing with the current decision tree to obtain the decision tree sum result, and update the current decision tree with the decision tree sum result; Obtain the preset maximum iteration update round, perform multiple iteration updates on the current decision tree until the maximum iteration update round is reached, and output the final current decision tree, so as to use the final current decision tree as a risk prediction model for financial derivatives trading.

[0010] In one possible design, the real-time financial derivatives trading data is used as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value for financial derivatives trading, including: The corresponding real-time fund flow data is extracted from the real-time financial derivatives pending transaction data as input, and the input is fed into the financial derivatives transaction risk prediction model. The corresponding financial derivatives transaction amount prediction value is generated through the financial derivatives transaction risk prediction model. Based on the real-time fund flow data in the real-time financial derivatives pending trading data and the predicted value of the financial derivatives trading amount output by the financial derivatives trading risk prediction model, the corresponding predicted value of financial derivatives liquidity risk is calculated. The real-time external market data, real-time transaction supervision data, and real-time counterparty credit data are extracted from the real-time financial derivatives pending transaction data. Based on the real-time external market data, the corresponding external market risk prediction value of financial derivatives is calculated. Based on the real-time transaction supervision data, the corresponding transaction operation risk prediction value of financial derivatives is calculated. Based on the real-time counterparty credit data, the corresponding credit risk prediction value of financial derivatives is calculated. Obtain preset liquidity risk weights, market risk weights, operational risk weights, and credit risk weights. Based on the liquidity risk weights, market risk weights, operational risk weights, and credit risk weights, perform a weighted summation of the predicted values ​​of the liquidity risk of the financial derivatives, the external market risk of the financial derivatives, the operational risk of the financial derivatives, and the credit risk of the financial derivatives to obtain the predicted value of the real-time risk index for financial derivatives trading.

[0011] In one possible design, based on the real-time financial derivatives trading data and the predicted real-time risk indicators for financial derivatives trading, a corresponding real-time trading strategy for financial derivatives is generated, including: Obtain a preset risk indicator threshold, compare the predicted real-time risk indicator value of the financial derivatives transaction with the risk indicator threshold, and obtain the comparison result; Obtain a preset hedging cost adjustment coefficient table, and select the corresponding hedging cost adjustment coefficient from the hedging cost adjustment coefficient table as the real-time hedging cost adjustment coefficient based on the comparison results. From the preset hedging strategy library, the real-time financial derivatives trading data and the predicted value of the real-time risk indicator of financial derivatives trading are used as query conditions to find the corresponding hedging strategy in the hedging strategy library as the real-time financial derivatives hedging strategy. The real-time financial derivatives hedging strategy is adjusted based on the real-time hedging cost adjustment coefficient to generate a corresponding real-time financial derivatives hedging strategy, and the real-time financial derivatives hedging strategy is used as the real-time financial derivatives trading strategy.

[0012] In one possible design, based on the real-time trading strategy for the financial derivatives, a corresponding trading management tool is invoked as a real-time risk control tool to execute the real-time trading strategy for the financial derivatives and complete the transaction, including: Based on the real-time hedging strategy for the financial derivatives, the corresponding transaction management tools are invoked as real-time risk control tools, wherein the transaction management tools include transaction execution tools, risk monitoring tools, fund management tools, and compliance verification tools; Based on the aforementioned real-time trading strategy for financial derivatives, the trading execution tool sends a trading request to the counterparty and executes the trading process. The risk monitoring tool monitors the trading process in real time, and the fund management tool allocates funds for the trading process to form a real-time trading record. The compliance verification tool verifies the compliance of the real-time trading record, and the trading of the financial derivatives is completed when the real-time trading record passes the compliance verification.

[0013] Secondly, the present invention provides an intelligent risk control system based on financial derivatives trading, including... The data acquisition unit is used to acquire historical financial derivatives trading data and real-time financial derivatives pending trading data. Each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information. The risk prediction unit is used to train a financial derivatives trading risk prediction model based on the historical financial derivatives trading data, and to input the real-time financial derivatives trading data into the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. The strategy generation unit is used to generate a corresponding real-time trading strategy for financial derivatives based on the real-time financial derivatives trading data and the predicted value of the real-time risk indicator for financial derivatives trading, wherein the real-time trading strategy for financial derivatives includes a real-time hedging strategy for financial derivatives. The transaction execution unit is used to invoke the corresponding transaction management tool as a real-time risk control tool according to the real-time trading strategy of the financial derivatives, so as to execute the real-time trading strategy of the financial derivatives and complete the transaction.

[0014] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the intelligent risk control method based on financial derivatives trading as described in the first aspect or any possible design of the first aspect.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the intelligent risk control method based on financial derivatives trading as described in the first aspect or any possible design of the first aspect.

[0016] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the intelligent risk control method based on financial derivatives trading as described in the first aspect or any possible design of the first aspect.

[0017] Beneficial Effects: This invention provides an intelligent risk control method and system based on financial derivatives trading, comprising: First, acquiring historical financial derivatives trading data and real-time financial derivatives pending trading data, wherein each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information; Second, training a financial derivatives trading risk prediction model based on the historical financial derivatives trading data, and inputting the real-time financial derivatives pending trading data into the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value; Then, generating a corresponding real-time financial derivatives trading strategy based on the real-time financial derivatives pending trading data and the real-time financial derivatives trading risk indicator prediction value, wherein the real-time financial derivatives trading strategy includes a real-time financial derivatives hedging strategy; Finally, according to the real-time financial derivatives trading strategy, calling a corresponding trading management tool as a real-time risk control tool to execute the real-time financial derivatives trading strategy and complete the transaction. By uniformly capturing and processing internal and external information, aligned and real-time integrated financial derivatives trading data is obtained. Through the integration of financial derivatives trading risk prediction models and risk control rules, the accuracy of real-time risk indicator predictions for financial derivatives trading is significantly improved. Based on these predictions, real-time and accurate real-time hedging strategies for financial derivatives trading are generated to enable dynamic adjustment of hedging strategies. Corresponding real-time risk control tools are then selected for corresponding transaction execution, achieving efficient risk control management of the trading process and improving the reliability of financial derivatives trading management. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the intelligent risk control method based on financial derivatives trading provided in an embodiment of the present invention; Figure 2 A functional structure diagram of an intelligent risk control system based on financial derivatives trading provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0020] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0021] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0022] Example: like Figure 1 As shown, the first aspect of this embodiment provides an intelligent risk control method based on financial derivatives trading, which may include, but is not limited to, the following steps: S1. Obtain historical financial derivatives trading data and real-time financial derivatives pending trading data, wherein each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information; In one possible implementation, step S1, which involves acquiring historical financial derivatives trading data and real-time financial derivatives pending trading data, can be broken down into steps S11-S15, including, but not limited to: S11. Through the enterprise financial management database, obtain the historical transaction records, historical risk event records, historical fund flow records and historical quota usage records corresponding to each completed financial derivative. Based on the historical transaction records, obtain the historical external market data, historical transaction regulatory data and historical counterparty credit data corresponding to each historical transaction record through the external API interface. S12. Obtain real-time cash flow data for each financial derivative to be traded through the enterprise financial management database, and obtain real-time external market data, real-time transaction supervision data and real-time counterparty credit data through external API interfaces; S13. For each completed financial derivative, the corresponding historical transaction records, historical risk event records, historical fund flow records, historical quota usage records, historical external market data, historical transaction regulatory data, and historical counterparty credit data are integrated into the original historical financial derivative transaction data. The original historical financial derivative transaction data is then cleaned and standardized to obtain the historical financial derivative transaction data. S14. For each financial derivative to be traded, the corresponding real-time fund flow data, real-time external market data, real-time transaction supervision data and real-time counterparty credit data are integrated into the original real-time financial derivative to be traded data, and the original real-time financial derivative to be traded data is cleaned and standardized to obtain the pre-real-time financial derivative to be traded data. S15. Obtain the preset transaction limit approval standard, and use the transaction limit approval standard to approve the real-time fund flow data in the pre-real-time financial derivative pending transaction data, so as to use the pre-real-time financial derivative pending transaction data that has passed the limit approval as the real-time financial derivative pending transaction data.

[0023] In practical applications, internal data includes full transaction data (contract type, transaction amount, open positions, delivery period, counterparty), financial data (capital utilization ratio, margin balance, profit and loss), and business data (the scale of spot business corresponding to hedging, price lock-in target). External data includes at least market data (interest rates, exchange rates, commodity prices, volatility index), regulatory data (new regulations, foreign exchange control policies), and counterparty data (credit rating, performance record, financial status). The system integrates trading systems (such as futures trading software, OTC derivatives trading platforms), financial ERP systems, risk control systems, and OA approval systems, achieving standardized data interfaces (real-time API synchronization). Preset synchronization frequencies are set for data collection, for example: real-time synchronization of transaction data, minute-by-minute updates of market data, daily updates of counterparty credit data, and weekly verification of regulatory data.

[0024] S2. Based on the historical financial derivatives trading data, train a financial derivatives trading risk prediction model, and input the real-time financial derivatives trading data as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. In one possible implementation, step S2, based on the historical financial derivatives trading data, trains a financial derivatives trading risk prediction model, which can be decomposed, but is not limited to, the following steps S21-S25, specifically including: S21. Extract the corresponding historical fund flow records and historical quota usage records from the historical financial derivatives transaction data as training data, wherein the training data uses the historical fund flow records as the target independent variable and the historical quota usage records as the target response variable. S22. Select the mean squared error as the loss function, and calculate the arithmetic mean of each target response variable in the training data to obtain the average value of the target response variable; S23. Obtain a preset decision tree model structure, establish an initial decision tree based on the decision tree model structure, take the average value of the target response variable corresponding to each target independent variable in the training data as the initial target prediction value of the initial decision tree, and calculate the corresponding initial decision tree residual based on the difference between the initial target prediction value and the target response variable corresponding to each target independent variable. S24. Based on the decision tree model structure, establish an updated decision tree, use the updated decision tree to perform residual fitting on the initial decision tree residual of the initial decision tree, and sum the updated decision tree and the initial decision tree after residual fitting to obtain the current decision tree; S25. With the goal of minimizing the loss function, the current decision tree is updated multiple times based on the training data to obtain a financial derivatives trading risk prediction model.

[0025] In one possible implementation, step S25, with the goal of minimizing the loss function, involves updating the current decision tree multiple times based on the training data to obtain a financial derivatives trading risk prediction model. This can be decomposed, but is not limited to, the following steps S251-S255, specifically including: S251. Use the current decision tree to predict each of the target independent variables in the training data, obtain the predicted output values ​​of multiple leaf nodes of the current decision tree, and calculate the average of the predicted output values ​​of each leaf node as the current decision tree prediction value. S252. Based on the current decision tree prediction value, the negative gradient of each target response variable is calculated using the following formula (1) to obtain the current decision tree residual value corresponding to each target independent variable: (1) in, For each of the aforementioned target independent variables index number, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree prediction value, Represent each of the stated target independent variables The corresponding target response variable, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree predictions and each of the stated target independent variables The corresponding loss function values ​​between the target response variables, This indicates the current decision tree's response to each of the stated objective variables. The residual value difference; S253. For the current decision tree, use the updated decision tree to learn the current decision tree's understanding of each of the target independent variables. The residual difference is learned, and the corresponding current update decision tree is trained using the training data with the goal of minimizing the loss function. S254. Obtain a preset decision tree learning rate, use the decision tree learning rate to perform weighted processing on the current updated decision tree, and sum the current updated decision tree after weighted processing with the current decision tree to obtain a decision tree summing result, and update the current decision tree with the decision tree summing result; S255. Obtain the preset maximum iteration update round, perform multiple iteration updates on the current decision tree until the maximum iteration update round is reached, and output the final current decision tree, so as to use the final current decision tree as a financial derivatives trading risk prediction model.

[0026] In one possible implementation, step S2, where the real-time financial derivatives trading data is used as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value for financial derivatives trading, can be broken down into steps S26-S29, specifically including: S26. Extract the corresponding real-time fund flow data from the real-time financial derivatives pending transaction data as input, input the input into the financial derivatives transaction risk prediction model, and generate the corresponding financial derivatives transaction amount prediction value through the financial derivatives transaction risk prediction model. S27. Based on the real-time fund flow data in the real-time financial derivatives pending transaction data and the financial derivatives transaction amount prediction value output by the financial derivatives transaction risk prediction model, calculate the corresponding financial derivatives liquidity risk prediction value. S28. Extract the corresponding real-time external market data, real-time transaction supervision data, and real-time counterparty credit data from the real-time financial derivatives pending transaction data; calculate the corresponding financial derivatives external market risk prediction value based on the real-time external market data; calculate the corresponding financial derivatives transaction operation risk prediction value based on the real-time transaction supervision data; and calculate the corresponding financial derivatives transaction credit risk prediction value based on the real-time counterparty credit data. S29. Obtain preset liquidity risk weights, market risk weights, operational risk weights, and credit risk weights. Based on the liquidity risk weights, market risk weights, operational risk weights, and credit risk weights, perform a weighted summation of the predicted values ​​of the liquidity risk of the financial derivatives, the predicted values ​​of the external market risk of the financial derivatives, the predicted values ​​of the operational risk of the financial derivatives, and the predicted values ​​of the credit risk of the financial derivatives to obtain the predicted values ​​of the real-time risk indicators for financial derivatives trading.

[0027] During the training phase of the financial derivatives trading risk prediction model, at least three years of historical financial derivatives trading data are used as training data. In possible designs, multi-dimensional feature vectors, including market risk factors, credit risk factors, liquidity risk factors, and operational risk factors, can be extracted from the historical financial derivatives trading data. With actual risk loss as the target variable, multiple decision trees of depth 4-6 are iteratively constructed to fit the risk function. Each tree learns the residual of the previous tree, and finally, a strong prediction model is obtained by weighted summation, which is used as the final financial derivatives trading risk prediction model. Before each transaction, the financial derivatives trading risk prediction model can be updated once for incremental training, and a certain full retraining cycle can be preset to avoid the impact of sudden changes in the external environment on the model's prediction.

[0028] S3. Based on the real-time financial derivatives pending trading data and the predicted value of the real-time risk indicator for financial derivatives trading, generate a corresponding real-time financial derivatives trading strategy, wherein the real-time financial derivatives trading strategy includes a real-time financial derivatives hedging strategy. In one possible implementation, step S3, based on the real-time financial derivatives trading data and the predicted value of the real-time risk indicator for financial derivatives trading, generates a corresponding real-time trading strategy for financial derivatives. This can be broken down into, but is not limited to, the following steps S31-S34, specifically including: S31. Obtain a preset risk indicator threshold, compare the predicted value of the real-time risk indicator for financial derivatives trading with the risk indicator threshold, and obtain the comparison result; S32. Obtain a preset hedging cost adjustment coefficient table, and select the corresponding hedging cost adjustment coefficient from the hedging cost adjustment coefficient table as the real-time hedging cost adjustment coefficient based on the comparison results. S33. From the preset hedging strategy library, the real-time financial derivatives pending trading data and the predicted value of the real-time risk indicator of financial derivatives trading are used as query conditions to find the corresponding hedging strategy in the hedging strategy library as the real-time financial derivatives hedging strategy. S34. Adjust the real-time financial derivative hedging strategy based on the real-time hedging cost adjustment coefficient to generate a corresponding real-time financial derivative hedging strategy for the financial derivative, and use the real-time financial derivative hedging strategy as the real-time financial derivative trading strategy.

[0029] S4. Based on the real-time trading strategy for financial derivatives, invoke the corresponding trading management tool as a real-time risk control tool to execute the real-time trading strategy for financial derivatives and complete the transaction.

[0030] In one possible implementation, step S4, based on the real-time trading strategy for financial derivatives, calls the corresponding trading control tool as a real-time risk control tool to execute the real-time trading strategy for financial derivatives and complete the transaction. This can be broken down into, but is not limited to, the following steps S41-S42, specifically including: S41. Based on the real-time hedging strategy for the financial derivatives, invoke the corresponding transaction management tool as a real-time risk control tool, wherein the transaction management tool includes a transaction execution tool, a risk monitoring tool, a fund management tool, and a compliance verification tool; S42. Based on the real-time trading strategy for financial derivatives, a trading application is sent to the counterparty and the trading process is executed through the trading execution tool. The trading process is monitored for real-time risk through the risk monitoring tool. The trading process is managed through the fund management tool to generate real-time trading records. The real-time trading records are verified for compliance through the compliance verification tool. The trading of the financial derivatives is completed when the real-time trading records pass the compliance verification.

[0031] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the intelligent risk control method based on financial derivatives trading as described in the first aspect of the embodiment, including: The data acquisition unit is used to acquire historical financial derivatives trading data and real-time financial derivatives pending trading data. Each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information. The risk prediction unit is used to train a financial derivatives trading risk prediction model based on the historical financial derivatives trading data, and to input the real-time financial derivatives trading data into the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. The strategy generation unit is used to generate a corresponding real-time trading strategy for financial derivatives based on the real-time financial derivatives trading data and the predicted value of the real-time risk indicator for financial derivatives trading, wherein the real-time trading strategy for financial derivatives includes a real-time hedging strategy for financial derivatives. The transaction execution unit is used to invoke the corresponding transaction management tool as a real-time risk control tool according to the real-time trading strategy of the financial derivatives, so as to execute the real-time trading strategy of the financial derivatives and complete the transaction.

[0032] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0033] like Figure 3 As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the intelligent risk control method based on financial derivatives trading as described in the first aspect of the embodiment.

[0034] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0035] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0036] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0037] The fourth aspect of this embodiment provides a storage medium for storing instructions containing the intelligent risk control method based on financial derivatives trading as described in the first aspect of the embodiment. That is, the storage medium stores instructions, and when the instructions are run on a computer, the intelligent risk control method based on financial derivatives trading as described in the first aspect of the embodiment is executed.

[0038] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0039] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0040] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the intelligent risk control method based on financial derivatives trading as described in the first aspect of this embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0041] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart risk control method based on financial derivatives trading, characterized in that, Acquire historical financial derivatives trading data and real-time financial derivatives pending trading data, wherein each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information; Based on the historical financial derivatives trading data, a financial derivatives trading risk prediction model is trained, and the real-time financial derivatives trading data is used as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. Based on the real-time financial derivatives pending trading data and the predicted real-time risk indicators for financial derivatives trading, a corresponding real-time financial derivatives trading strategy is generated, wherein the real-time financial derivatives trading strategy includes a real-time financial derivatives hedging strategy. Based on the real-time trading strategy for the financial derivatives, the corresponding trading management tool is invoked as a real-time risk control tool to execute the real-time trading strategy for the financial derivatives and complete the transaction.

2. The intelligent risk control method based on financial derivatives trading according to claim 1, characterized in that, Obtain historical financial derivatives trading data and real-time financial derivatives pending trading data, including: Through the enterprise financial management database, obtain historical transaction records, historical risk event records, historical fund flow records, and historical credit limit usage records corresponding to each completed financial derivative transaction. Based on the historical transaction records, obtain historical external market data, historical transaction regulatory data, and historical counterparty credit data corresponding to each historical transaction record through external API interfaces. By using the corporate financial management database, we can obtain real-time cash flow data for each financial derivative product to be traded, and obtain real-time external market data, real-time transaction supervision data, and real-time counterparty credit data through external API interfaces. For each completed financial derivative transaction, the corresponding historical transaction records, historical risk event records, historical fund flow records, historical quota usage records, historical external market data, historical transaction regulatory data, and historical counterparty credit data are integrated into the original historical financial derivative transaction data. The original historical financial derivative transaction data is then cleaned and standardized to obtain the historical financial derivative transaction data. For each financial derivative to be traded, the corresponding real-time fund flow data, real-time external market data, real-time transaction supervision data, and real-time counterparty credit data are integrated into the original real-time financial derivative to be traded data. The original real-time financial derivative to be traded data is then cleaned and standardized to obtain the pre-real-time financial derivative to be traded data. Obtain preset transaction limit approval criteria, and use the transaction limit approval criteria to approve the real-time fund flow data in the pre-real-time financial derivatives pending transaction data, so as to use the pre-real-time financial derivatives pending transaction data that has passed the limit approval as the real-time financial derivatives pending transaction data.

3. The intelligent risk control method based on financial derivatives trading according to claim 1, characterized in that, Based on the aforementioned historical financial derivatives trading data, a financial derivatives trading risk prediction model is trained, including: The corresponding historical fund flow records and historical quota usage records are extracted from the historical financial derivatives transaction data as training data, wherein the training data uses the historical fund flow records as the target independent variable and the historical quota usage records as the target response variable. Mean squared error is selected as the loss function, and the arithmetic mean of each target response variable in the training data is calculated to obtain the average value of the target response variable; Obtain a preset decision tree model structure, establish an initial decision tree based on the decision tree model structure, take the average value of the target response variable corresponding to each target independent variable in the training data as the initial target prediction value of the initial decision tree, and calculate the corresponding initial decision tree residual based on the difference between the initial target prediction value and the target response variable corresponding to each target independent variable. Based on the decision tree model structure, an updated decision tree is established. The updated decision tree is used to fit the residual of the initial decision tree of the initial decision tree. The updated decision tree and the initial decision tree after the residual fitting are summed to obtain the current decision tree. With the goal of minimizing the loss function, the current decision tree is updated multiple times based on the training data to obtain a financial derivatives trading risk prediction model.

4. The intelligent risk control method based on financial derivatives trading according to claim 3, characterized in that, With the goal of minimizing the loss function, the current decision tree is updated multiple times based on the training data to obtain a financial derivatives trading risk prediction model, including: The current decision tree is used to predict each of the target independent variables in the training data, and the predicted output values ​​of multiple leaf nodes of the current decision tree are obtained. The mean of the predicted output values ​​of each leaf node is calculated as the current decision tree prediction value. Based on the current decision tree prediction value, the negative gradient of each target response variable is calculated using the following formula (1) to obtain the current decision tree residual value corresponding to each target independent variable: （1） in, For each of the aforementioned target independent variables index number, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree prediction value, Represent each of the stated target independent variables The corresponding target response variable, This indicates the current decision tree's response to each of the stated objective variables. The current decision tree predictions and each of the stated target independent variables The corresponding loss function values ​​between the target response variables, This indicates the current decision tree's response to each of the stated objective variables. The residual value difference; For the current decision tree, the updated decision tree is used to apply the changes to each of the target independent variables. The residual difference is learned, and the corresponding current update decision tree is trained using the training data with the goal of minimizing the loss function. Obtain a preset decision tree learning rate, use the decision tree learning rate to perform weighted processing on the current updated decision tree, and sum the current updated decision tree after weighted processing with the current decision tree to obtain the decision tree sum result, and update the current decision tree with the decision tree sum result; Obtain the preset maximum iteration update round, perform multiple iteration updates on the current decision tree until the maximum iteration update round is reached, and output the final current decision tree, so as to use the final current decision tree as a risk prediction model for financial derivatives trading.

5. The intelligent risk control method based on financial derivatives trading according to claim 1, characterized in that, The real-time financial derivatives trading data is used as input to the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value for financial derivatives trading, including: The corresponding real-time fund flow data is extracted from the real-time financial derivatives pending transaction data as input, and the input is fed into the financial derivatives transaction risk prediction model. The corresponding financial derivatives transaction amount prediction value is generated through the financial derivatives transaction risk prediction model. Based on the real-time fund flow data in the real-time financial derivatives pending trading data and the predicted value of the financial derivatives trading amount output by the financial derivatives trading risk prediction model, the corresponding predicted value of financial derivatives liquidity risk is calculated. The real-time external market data, real-time transaction supervision data, and real-time counterparty credit data are extracted from the real-time financial derivatives pending transaction data. Based on the real-time external market data, the corresponding external market risk prediction value of financial derivatives is calculated. Based on the real-time transaction supervision data, the corresponding transaction operation risk prediction value of financial derivatives is calculated. Based on the real-time counterparty credit data, the corresponding credit risk prediction value of financial derivatives is calculated. Obtain preset liquidity risk weights, market risk weights, operational risk weights, and credit risk weights. Based on the liquidity risk weights, market risk weights, operational risk weights, and credit risk weights, perform a weighted summation of the predicted values ​​of the liquidity risk of the financial derivatives, the external market risk of the financial derivatives, the operational risk of the financial derivatives, and the credit risk of the financial derivatives to obtain the predicted value of the real-time risk index for financial derivatives trading.

6. The intelligent risk control method based on financial derivatives trading according to claim 1, characterized in that, Based on the real-time pending trading data of financial derivatives and the predicted real-time risk indicators for financial derivatives trading, a corresponding real-time trading strategy for financial derivatives is generated, including: Obtain a preset risk indicator threshold, compare the predicted real-time risk indicator value of the financial derivatives transaction with the risk indicator threshold, and obtain the comparison result; Obtain a preset hedging cost adjustment coefficient table, and select the corresponding hedging cost adjustment coefficient from the hedging cost adjustment coefficient table as the real-time hedging cost adjustment coefficient based on the comparison results. From the preset hedging strategy library, the real-time financial derivatives trading data and the predicted value of the real-time risk indicator of financial derivatives trading are used as query conditions to find the corresponding hedging strategy in the hedging strategy library as the real-time financial derivatives hedging strategy. The real-time financial derivatives hedging strategy is adjusted based on the real-time hedging cost adjustment coefficient to generate a corresponding real-time financial derivatives hedging strategy, and the real-time financial derivatives hedging strategy is used as the real-time financial derivatives trading strategy.

7. The intelligent risk control method based on financial derivatives trading according to claim 1, characterized in that, According to the real-time trading strategy for financial derivatives, the corresponding trading management tool is invoked as a real-time risk control tool to execute the real-time trading strategy for financial derivatives and complete the transaction, including: Based on the real-time hedging strategy for the financial derivatives, the corresponding transaction management tools are invoked as real-time risk control tools, wherein the transaction management tools include transaction execution tools, risk monitoring tools, fund management tools, and compliance verification tools; Based on the aforementioned real-time trading strategy for financial derivatives, the trading execution tool sends a trading request to the counterparty and executes the trading process. The risk monitoring tool monitors the trading process in real time, and the fund management tool allocates funds for the trading process to form a real-time trading record. The compliance verification tool verifies the compliance of the real-time trading record, and the trading of the financial derivatives is completed when the real-time trading record passes the compliance verification.

8. An intelligent risk control system based on financial derivatives trading, characterized in that, The intelligent risk control method based on financial derivatives trading as described in any one of claims 1 to 7 includes: The data acquisition unit is used to acquire historical financial derivatives trading data and real-time financial derivatives pending trading data. Each piece of historical financial derivatives trading data includes corresponding historical financial derivatives trading internal information, historical financial derivatives trading external information, and historical financial derivatives trading strategy information. The risk prediction unit is used to train a financial derivatives trading risk prediction model based on the historical financial derivatives trading data, and to input the real-time financial derivatives trading data into the financial derivatives trading risk prediction model to obtain the corresponding real-time risk indicator prediction value of financial derivatives trading. The strategy generation unit is used to generate a corresponding real-time trading strategy for financial derivatives based on the real-time financial derivatives trading data and the predicted value of the real-time risk indicator for financial derivatives trading, wherein the real-time trading strategy for financial derivatives includes a real-time hedging strategy for financial derivatives. The transaction execution unit is used to invoke the corresponding transaction management tool as a real-time risk control tool according to the real-time trading strategy of the financial derivatives, so as to execute the real-time trading strategy of the financial derivatives and complete the transaction.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the intelligent risk control method based on financial derivatives trading as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the intelligent risk control method based on financial derivatives trading as described in any one of claims 1 to 7.

Images