Financial derivative pricing and risk management system and method based on artificial intelligence
Through dynamic weighted volatility algorithm and improved Monte Carlo simulation method, combined with transaction volume and time decay factors, the inaccuracy problem of traditional volatility calculation and risk assessment is solved, and more accurate pricing and risk management of financial derivatives are achieved. , improves the adaptability and effectiveness of risk hedging.
Patent Information
- Application Number
- CN202410961780.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional volatility calculation methods tend to ignore transaction volume and time decay factors, resulting in inaccurate volatility calculation; traditional financial derivatives pricing algorithms do not fully consider the expected yield and volatility of the underlying assets, resulting in low pricing accuracy; existing markets Risk assessment methods are difficult to accurately capture the complex dynamic changes in the market, resulting in inaccurate risk assessment; existing risk hedging strategies rely on static hedging models and lack timely responses to market dynamic changes, resulting in unsatisfactory hedging results.
Use dynamic weighted volatility algorithm to calculate the volatility of the underlying asset, combining transaction volume and time decay factors; use the improved Monte Carlo simulation method to calculate the risk value, comprehensively consider the volatility, transaction volume and holding period of financial derivatives; When the risk value exceeds the set threshold, a dynamic nonlinear hedging algorithm is used to determine the risk amount that needs to be hedged, and a suitable risk tool is selected for risk hedging.
It improves the accuracy of pricing of financial derivatives and the accuracy of risk assessment, enhances market trust and participation; improves the adaptability and effectiveness of risk hedging strategies, reduces market risks, and optimizes the hedging effect.
Smart Images

Figure CN118917873A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence, and in particular to an artificial intelligence-based financial derivatives pricing and risk management system and method. Background Art
[0002] With the rapid development of financial markets and the strengthening of globalization, financial derivatives, as important risk management tools and investment methods, have become increasingly important in the financial market. However, the pricing and risk management of financial derivatives have always been difficult issues in the financial field. In recent years, the rapid development of artificial intelligence technology has provided new ideas and methods for the pricing and risk management of financial derivatives, and financial derivatives pricing and risk management systems based on artificial intelligence have emerged.
[0003] The AI-based financial derivatives pricing and risk management system can make full use of the advantages of AI technology. Through powerful data processing and analysis capabilities, it can provide strong technical support for the accurate pricing and effective risk management of financial derivatives, improve the accuracy of financial derivatives pricing and the efficiency of risk management, and provide strong support for the stable development of the financial market.
[0004] The Chinese patent with application number CN202010274570.5 and publication date of August 25, 2020, discloses a financial risk management method based on GBST, including: obtaining a historical user data set, establishing a training data set based on the historical user data set, wherein the training data set includes user feature data, conditional parameters, and financial performance data; constructing a GBST survival model, and training the GBST survival model; inputting the user feature data and conditional parameters of the target user into the GBST survival model to output a predicted distribution curve of the target user's financial performance data; based on the predicted distribution curve of the target user, according to the maximum profit judgment rule of the financial product, customizing a risk management strategy corresponding to the target user. The financial risk management method of the invention aims to maximize profits, can formulate more personalized and more reasonable products for users, can optimize the existing risk management strategies of quota, pricing and period, and generate more profits under the condition that risks are controllable to achieve profit maximization.
[0005] However, the above technologies have at least the following technical problems: the traditional volatility calculation method tends to ignore the trading volume and time decay factors, resulting in inaccurate volatility calculation; the traditional financial derivatives pricing algorithm does not fully consider the expected return and volatility of the underlying assets, resulting in low pricing accuracy; the existing market risk assessment methods are difficult to accurately capture the complex dynamic changes in the market, resulting in inaccurate risk assessment; the existing risk hedging strategies rely on static hedging models and lack timely response to dynamic changes in the market, resulting in unsatisfactory hedging effects. Summary of the invention
[0006] The present invention provides an artificial intelligence-based financial derivatives pricing and risk management system to solve the problems that the existing traditional volatility calculation method easily ignores the transaction volume and time decay factors, resulting in inaccurate volatility calculation; the traditional financial derivatives pricing algorithm does not fully consider the expected rate of return and volatility of the underlying assets, resulting in low pricing accuracy; the existing market risk assessment method is difficult to accurately capture the complex dynamic changes of the market, resulting in inaccurate risk assessment; the existing risk hedging strategy relies on a static hedging model and lacks timely response to dynamic changes in the market, resulting in unsatisfactory hedging effect.
[0007] An artificial intelligence-based financial derivatives pricing and risk management method disclosed in an embodiment of the present invention comprises the following steps:
[0008] S 1: Obtain financial market data from the data source, and calculate volatility using a dynamic weighted volatility algorithm based on the financial market data to obtain the volatility of the underlying asset;
[0009] S2: Based on financial market data and the volatility of the underlying asset, the price of financial derivatives is calculated using the financial derivatives pricing algorithm;
[0010] S3: Based on financial market data, the volatility of the underlying assets and the price of financial derivatives, the improved Monte Carlo simulation method is used to calculate the risk value;
[0011] S4: Set a risk threshold. When the risk value exceeds the set risk threshold, adopt a risk hedging strategy. The risk hedging strategy is based on financial market data and risk value. It uses a dynamic nonlinear hedging algorithm to determine the amount of risk that needs to be hedged and selects risk tools for risk hedging.
[0012] As a specific implementation, in step S1:
[0013] Financial market data include underlying asset prices, underlying asset trading volumes, and expiration dates of financial derivatives;
[0014] The dynamic weighted volatility algorithm weights the historical price data of the underlying asset by combining the underlying asset's trading volume and time decay factors.
[0015] As a specific implementation, in step S1, calculating the volatility of the underlying asset includes the following steps:
[0016] The price of the underlying asset within a given time window is weighted by the weighting coefficient and then averaged to obtain the weighted average of the historical price of the underlying asset;
[0017] Based on the weighted mean of the underlying asset price and the historical price of the underlying asset, and the sum of the weighted coefficients, the weighted sum of squared deviations is obtained;
[0018] The volatility of the underlying asset is obtained by taking the square root of the sum of the weighted deviations divided by the sum of the weighting coefficients.
[0019] As a specific implementation, the weighting coefficient of a certain calculation time point within a given time window is obtained by multiplying the ratio of the underlying asset trading volume at the calculation time point to the total underlying asset trading volume within the given time window by the time decay weight;
[0020] The time decay weight is obtained based on a parameter characterizing the speed of controlling the time decay and a parameter characterizing the distance between the calculation time point and the current time point.
[0021] As a specific implementation, in step S2, the price of financial derivatives is calculated by combining the expected rate of return and volatility of the underlying asset with the financial derivative pricing algorithm, introducing a dynamic adjustment coefficient and a cumulative probability calculation of a standard normal distribution function.
[0022] As a specific implementation, in step S3, the improved Monte Carlo simulation method is obtained based on the volatility of the underlying asset, the trading volume of the underlying asset and the holding period of the financial derivative.
[0023] As a specific implementation, step S4 specifically includes setting a risk threshold. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted. The risk hedging strategy needs to determine the amount of risk to be hedged and select a risk tool for risk hedging.
[0024] As a specific implementation, in step S4, the amount of risk to be hedged is calculated by a dynamic nonlinear hedge algorithm based on the price of the underlying asset, the trading volume of the underlying asset and the time decay factor, using a sine function, a square root ratio and a logic function.
[0025] Another embodiment of the present application further discloses an artificial intelligence-based financial derivatives pricing and risk management system, which applies an artificial intelligence-based financial derivatives pricing and risk management method. The artificial intelligence-based financial derivatives pricing and risk management system includes:
[0026] A financial market data acquisition module, used to acquire financial market data from a data source;
[0027] The volatility calculation module is used to receive the financial market data from the financial market data acquisition module, and calculate the volatility using a dynamic weighted volatility algorithm based on the financial market data to obtain the volatility of the underlying asset;
[0028] The financial derivatives pricing module receives the financial market data from the financial market data acquisition module and the volatility of the underlying asset from the volatility calculation module, and calculates the price of the financial derivatives using the financial derivatives pricing algorithm based on the financial market data and the volatility of the underlying asset;
[0029] A risk value calculation module receives the financial market data from the financial market data acquisition module, the volatility of the underlying asset from the volatility calculation module, and the price of the financial derivatives from the financial derivatives pricing module, and calculates the risk value based on the financial market data, the volatility of the underlying asset, and the price of the financial derivatives using an improved Monte Carlo simulation method;
[0030] The risk hedging module is used to set the risk threshold, receive the risk value calculated by the risk value calculation module, and compare the risk value with the risk threshold. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted; the risk hedging strategy is based on the financial market data of the financial market data acquisition module and the risk value of the risk value calculation module, and uses a dynamic nonlinear hedging amount algorithm to determine the amount of risk that needs to be hedged, and selects risk tools for risk hedging.
[0031] The beneficial effects of the technical solution of the present invention are:
[0032] 1. Use the dynamic weighted volatility algorithm to weight the historical price data according to the underlying asset's trading volume and time decay factors to calculate the volatility of the underlying asset, which can reflect the true volatility of the market and provide accurate parameters for pricing and risk assessment of financial derivatives.
[0033] 2. By utilizing the volatility of the underlying assets and calculating the price of derivatives through the financial derivatives pricing algorithm, the pricing accuracy of financial derivatives is improved, so that accuracy can be maintained in different market environments, and the market's trust and participation are increased.
[0034] 3. The improved Monte Carlo simulation method is adopted to comprehensively consider the volatility of the underlying assets, trading volume and holding period of financial derivatives. The risk value is calculated through the application of logarithmic functions and exponential functions. It can accurately assess market risks, improve the accuracy and sensitivity of risk value calculation, and help investors better understand and manage market risks.
[0035] 4. Use a dynamic nonlinear hedging algorithm to determine the amount of risk that needs to be hedged, and select appropriate risk tools for hedging, which reduces market risk, optimizes hedging effects, and improves the adaptability and effectiveness of risk hedging strategies. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 This is a structural diagram of an artificial intelligence-based financial derivatives pricing and risk management system according to an embodiment of the present invention;
[0037] Figure 2 This is a flowchart of an artificial intelligence-based financial derivatives pricing and risk management method according to another embodiment of the present invention. DETAILED DESCRIPTION
[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all 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.
[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0040] The specific scheme of the artificial intelligence-based financial derivatives pricing and risk management system provided by the present invention is described in detail below with reference to the accompanying drawings.
[0041] Refer to the attached Figure 1 The artificial intelligence-based financial derivatives pricing and risk management system provided in an embodiment of the present invention includes a financial market data acquisition module, a volatility calculation module, a financial derivatives pricing module, a risk value calculation module, and a risk hedging module.
[0042] The financial market data acquisition module is used to acquire financial market data from the data source through application program interface calls, and output the financial market data to the volatility calculation module, financial derivatives pricing module, risk value calculation module and risk hedging module.
[0043] The volatility calculation module is used to calculate the volatility based on the financial market data of the financial market data acquisition module, adopt the dynamic weighted volatility algorithm to obtain the volatility of the underlying asset, and output the volatility of the underlying asset to the financial derivatives pricing module and the risk value calculation module.
[0044] The financial derivatives pricing module is used to receive the financial market data from the financial market data acquisition module and the volatility of the underlying asset calculated by the volatility calculation module, use the financial derivatives pricing algorithm to calculate the financial derivatives price, and output the financial derivatives price to the risk value calculation module.
[0045] The risk value calculation module is used to receive the financial market data from the financial market data acquisition module, the volatility of the underlying asset calculated by the volatility calculation module and the price of the financial derivatives calculated by the financial derivatives pricing module, calculate the risk value using the improved Monte Carlo simulation method, and output the risk value to the risk hedging module.
[0046] The risk hedging module is used to set the risk threshold. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted. The risk hedging strategy is based on the financial market data obtained by the financial market data acquisition module and the risk value calculated by the risk value calculation module. A dynamic nonlinear hedging algorithm is used to determine the amount of risk that needs to be hedged, and risk tools are selected for risk hedging.
[0047] Refer to the attached Figure 2 Another embodiment of the present invention provides a financial derivatives pricing and risk management method based on artificial intelligence, comprising the following steps:
[0048] S1. Obtain financial market data from a data source, and based on the financial market data, use a dynamic weighted volatility algorithm to calculate volatility to obtain the volatility of the underlying asset.
[0049] Specifically, financial market data in data sources are obtained through application program interface calls; illustratively, data sources include official exchange websites, financial data service providers, online financial platforms, social media and forums; financial market data include underlying asset prices, underlying asset trading volumes, and expiration times of financial derivatives.
[0050] In order to reflect the real volatility of the market, a dynamic weighted volatility algorithm is used to calculate volatility based on financial market data to obtain the volatility of the underlying asset. The dynamic weighted volatility algorithm weights the historical price data of the underlying asset by combining the trading volume and time decay factors of the underlying asset to provide accurate and real-time volatility of the underlying asset.
[0051] The specific calculation formula of the volatility of the underlying asset is:
[0052]
[0053] Where v represents the volatility of the underlying asset; represents the square root symbol, which is used to square the mean of the sum of squared weighted deviations so that the volatility of the underlying asset has the same dimension as the unit of the underlying asset price; represents the sum of weighting coefficients; represents the weighted sum of squared deviations, reflecting the degree to which the price deviates from the mean; T represents the total number of time points in the time window; P t represents the price of the underlying asset at time point t; Represents the weighted mean of the historical prices of the underlying asset, where the weighted mean of the historical prices of the underlying asset is the weighted average of the historical prices of the underlying asset within a given time window, which is used to reflect the central trend of the historical prices of the underlying asset. The specific calculation formula of the weighted mean of the historical prices of the underlying asset is:
[0054]
[0055] Among them, w t It represents the weighting coefficient at time point t. The weighting coefficient at time point t comprehensively considers the underlying asset trading volume and time decay factors, and is used to assign different weights to the historical prices of the underlying asset at different time points, reflecting the impact of the underlying asset trading volume and time on the volatility of the underlying asset. The specific calculation formula of the weighting coefficient at time point t is:
[0056]
[0057] in, Represents the trading volume weight of the underlying asset, which is the trading volume V of the underlying asset at time point t t Total trading volume with the underlying asset Compared with, it is used to reflect the market participation at time point t; V t represents the trading volume of the underlying asset at time point t; e -λτ represents the time decay weight; λ represents the parameter that controls the time decay speed; τ represents the distance between the time point t and the current time.
[0058] The volatility of the underlying asset is an important parameter for pricing financial derivatives. Accurate volatility of the underlying asset can improve the accuracy of pricing of financial derivatives and provide a scientific basis for investment decisions.
[0059] S2. Based on financial market data and the volatility of the underlying assets, the financial derivatives pricing algorithm is used to calculate the price of financial derivatives.
[0060] Financial market data includes current underlying asset prices, historical underlying asset data, and expiration dates of financial derivatives.
[0061] The financial derivatives pricing algorithm combines the expected return and volatility of the underlying assets. By introducing a dynamic adjustment coefficient and the cumulative probability of the standard normal distribution function, it can improve the accuracy and applicability of financial derivatives pricing, improve the pricing precision of financial derivatives, maintain accuracy in different market environments, and help increase market trust and participation.
[0062] The specific calculation formula for the price of financial derivatives is:
[0063]
[0064] Among them, Q represents the price of financial derivatives; P′ represents the current price of the underlying asset; represents the impact of the expected rate of return u of the underlying asset and the volatility v of the underlying asset on the price of financial derivatives; e is the base of the natural logarithm, which is used to represent the growth process of continuous compound interest; u represents the expected rate of return of the underlying asset, which is predicted based on the historical data of the underlying asset using a regression analysis algorithm. The regression analysis algorithm is a technical means well known to those skilled in the art and will not be described in detail here; v represents the volatility of the underlying asset; Indicates the expiration time of financial derivatives; a represents the coefficient that adjusts the impact of the volatility of the underlying asset on the price of financial derivatives, which is used to improve the accuracy of financial derivatives pricing; Represents the square root of the expiration time of financial derivatives, so that the impact of expiration time on the volatility of the underlying asset remains moderate, reflecting the actual market behavior; represents the cumulative probability of the standard normal distribution function, which is used to calculate the probability component of the price of financial derivatives; Φ represents the cumulative probability function of the standard normal distribution function; ln(P′) represents the natural logarithm of the price of the underlying asset. The logarithmic transformation helps to stabilize the volatility of the price of the underlying asset; Indicates the expected rate of return of the underlying asset at the expiration date of the financial derivative. The cumulative return reflects the market's expectation of the performance of the underlying asset at maturity; An adjustment term representing the volatility of the underlying asset to reflect the uncertainty caused by the price fluctuations of the underlying asset; It represents the product of the volatility of the underlying asset and the square root of the expiration time of the financial derivative. It is used for normalization and reflects the uncertainty amplification effect of the expiration time of the financial derivative on the price fluctuation of the underlying asset.
[0065] The price of financial derivatives is calculated through the financial derivatives pricing algorithm, which improves pricing accuracy, enhances the market's trust and participation in financial derivatives pricing, and provides comprehensive and reliable data support for risk assessment, ensuring the accuracy of risk value calculation.
[0066] S3. Based on financial market data, the volatility of the underlying assets and the prices of financial derivatives, the improved Monte Carlo simulation method is used to calculate the risk value.
[0067] In order to accurately assess market risks and improve the accuracy of risk value calculation, the improved Monte Carlo simulation method is used to calculate the risk value based on financial market data, the volatility of the underlying assets and the prices of financial derivatives.
[0068] Financial market data include initial underlying asset prices, holding periods of financial derivatives, and underlying asset trading volumes.
[0069] The improved Monte Carlo simulation method comprehensively considers the volatility of the underlying asset, the trading volume of the underlying asset, and the holding period of the financial derivatives to accurately assess market risk. Through the application of logarithmic and exponential functions, the formula can capture the complex dynamic changes of the market, making risk assessment accurate and sensitive.
[0070] The formula for calculating the risk value is:
[0071]
[0072] Among them, R represents the risk value, which is used to quantify market risk; Q represents the price of financial derivatives; e represents the base of natural logarithm, which is used for exponential function calculation to reflect the continuous compound growth or decay process; α represents the parameter for adjusting market volatility, which is used to adjust the sensitivity of risk value to volatility; v represents the volatility of the underlying asset; Δt represents the holding period of financial derivatives; represents the square root of the holding period of a financial derivative; β represents the adjustment factor of the underlying asset trading volume to the risk value, which adjusts the risk value calculation to take into account market activity; V t represents the trading volume of the underlying asset at time point t, as an indicator of market activity; represents a logarithmic function, which is used to process the ratio of the underlying asset trading volume to the initial underlying asset price to adapt to market fluctuations; P0 represents the initial underlying asset price; The composite part of the exponential function representing the volatility of the underlying asset and the holding period of the financial derivative improves the adjustment ability of the volatility of the underlying asset under different time spans and captures complex market dynamics.
[0073] S4. Based on financial market data and risk value, a dynamic nonlinear hedging algorithm is used to determine the amount of risk that needs to be hedged, and risk tools are selected for risk hedging.
[0074] Specifically, a risk threshold is set. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted. If the risk value does not exceed the set risk threshold, there is no need to adopt a risk hedging strategy. The risk threshold can be set according to the specific implementation scenario and is not limited here.
[0075] Furthermore, the risk hedging strategy requires determining the amount of risk to be hedged and selecting risk instruments to hedge the risk.
[0076] Specifically, based on financial market data and risk value, a dynamic nonlinear hedging algorithm is used to determine the amount of risk that needs to be hedged; financial market data include the initial underlying asset price, the underlying asset trading volume, and the underlying asset price.
[0077] The dynamic nonlinear hedging algorithm takes into account the underlying asset price, underlying asset trading volume and time decay factors, and uses sine functions, square root ratios and logic functions to calculate the required hedging risk amount, so that the hedging risk amount can be dynamically adjusted according to market conditions, thereby improving the accuracy and flexibility of hedging.
[0078] The specific calculation formula for the hedged risk amount is:
[0079]
[0080] Where H represents the amount of risk hedged; It represents the ratio of the risk value to the initial underlying asset price change to determine the initial hedge amount; R represents the risk value, which is used to quantify market risk; P0 represents the initial underlying asset price; sin(ct) represents the sine function, which introduces the periodic change of time so that the hedged risk amount can be adjusted dynamically over time; c represents the time decay parameter, which controls the time decay speed and affects the frequency of the sine function; V represents the square root ratio of the underlying asset's trading volume, reflecting the impact of the underlying asset's trading volume at time point t relative to the maximum trading volume; t V represents the trading volume of the underlying asset at time point t; max Indicates the maximum trading volume, providing a standardized benchmark for the underlying asset’s trading volume; It represents the influencing factor of the underlying asset price change rate. It introduces the nonlinear impact of the underlying asset price change rate so that the hedged risk volume can reflect the dynamic changes of market prices. k represents the adjustment coefficient of the underlying asset price change amplitude. ΔP represents the underlying asset price change amplitude within the time window. The time window can be set according to the specific implementation scenario and is not limited here.
[0081] The specific risk hedging strategy is to calculate the amount of risk to be hedged through a dynamic nonlinear hedging algorithm, and select risk tools for risk hedging. For example, risk tools include futures contracts, asset-backed securities, and government bonds. The specific risk tools used are not limited here; specifically, according to the calculated hedging risk amount, a number of futures contracts specified by professionals can be bought or sold.
[0082] By adopting nonlinear hedging volume algorithms to conduct scientific and dynamic risk hedging, market risks can be reduced, hedging effects can be optimized, and the adaptability and effectiveness of risk hedging strategies can be improved.
[0083] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0084] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. Pricing and risk management methods of financial derivatives based on artificial intelligence, It is characterized in that The following steps are involved: S1: Obtain financial market data from the data source, and calculate volatility using a dynamic weighted volatility algorithm based on the financial market data to obtain the volatility of the underlying asset; S2: Based on financial market data and the volatility of the underlying asset, the price of financial derivatives is calculated using the financial derivatives pricing algorithm; S3: Based on financial market data, the volatility of the underlying assets and the price of financial derivatives, the improved Monte Carlo simulation method is used to calculate the risk value; S4: Set a risk threshold. When the risk value exceeds the set risk threshold, adopt a risk hedging strategy. The risk hedging strategy is based on financial market data and risk value. It uses a dynamic nonlinear hedging algorithm to determine the amount of risk that needs to be hedged and selects risk tools for risk hedging.
2. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 1, It is characterized in that In step S1: Financial market data include underlying asset prices, underlying asset trading volumes, and expiration dates of financial derivatives; The dynamic weighted volatility algorithm weights the historical price data of the underlying asset by combining the underlying asset's trading volume and time decay factors.
3. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 2, It is characterized in that In step S1, calculating the volatility of the underlying asset includes the following steps: The price of the underlying asset within a given time window is weighted by the weighting coefficient and then averaged to obtain the weighted average of the historical price of the underlying asset; Based on the weighted average of the price of the underlying asset and the historical price of the underlying asset, and the sum of the weighted coefficients, a weighted sum of squared deviations is obtained; The volatility of the underlying asset is obtained by taking the square root of the sum of the weighted deviations divided by the sum of the weighting coefficients.
4. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 3, It is characterized in that The weighting coefficient of a calculation time point within a given time window is obtained by multiplying the ratio of the underlying asset trading volume at the calculation time point to the total underlying asset trading volume within the given time window by the time decay weight; The time decay weight is obtained based on a parameter characterizing the speed of controlling the time decay and a parameter characterizing the distance between the calculation time point and the current time point.
5. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 1, It is characterized in that In step S2, the price of financial derivatives is calculated by combining the expected rate of return and volatility of the underlying asset with the financial derivative pricing algorithm, and introducing a dynamic adjustment coefficient and a cumulative probability calculation of the standard normal distribution function.
6. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 1, It is characterized in that In step S3, the improved Monte Carlo simulation method is obtained based on the volatility of the underlying asset, the trading volume of the underlying asset and the holding period of the financial derivative.
7. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 1, It is characterized in that Step S4 specifically includes setting a risk threshold. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted. The risk hedging strategy needs to determine the amount of risk to be hedged and select a risk tool for risk hedging.
8. The artificial intelligence-based financial derivatives pricing and risk management method according to claim 1, It is characterized in that In step S4, the risk amount to be hedged is calculated by a dynamic nonlinear hedge amount algorithm based on the underlying asset price, the underlying asset trading volume and the time decay factor, using the sine function, square root ratio and logic function.
9. An artificial intelligence-based financial derivatives pricing and risk management system. It is characterized in that The artificial intelligence-based financial derivatives pricing and risk management method according to any one of claims 1 to 8 is applied, wherein the artificial intelligence-based financial derivatives pricing and risk management system comprises: A financial market data acquisition module, used to acquire financial market data from a data source; A volatility calculation module, configured to receive the financial market data from the financial market data acquisition module, and perform volatility calculation based on the financial market data using a dynamic weighted volatility algorithm to obtain the volatility of the underlying asset; A financial derivative pricing module receives the financial market data from the financial market data acquisition module and the volatility of the underlying asset from the volatility calculation module, and calculates the price of the financial derivative using a financial derivative pricing algorithm based on the financial market data and the volatility of the underlying asset; a risk value calculation module, receiving the financial market data from the financial market data acquisition module, the volatility of the underlying asset from the volatility calculation module, and the price of the financial derivatives from the financial derivatives pricing module, and calculating the risk value by adopting an improved Monte Carlo simulation method based on the financial market data, the volatility of the underlying asset, and the price of the financial derivatives; The risk hedging module is used to set a risk threshold, receive the risk value calculated by the risk value calculation module, and compare the risk value with the risk threshold. When the risk value exceeds the set risk threshold, a risk hedging strategy is adopted; the risk hedging strategy is based on the financial market data of the financial market data acquisition module and the risk value of the risk value calculation module, and a dynamic nonlinear hedging amount algorithm is used to determine the amount of risk that needs to be hedged, and a risk tool is selected for risk hedging.
Citation Information
Patent Citations
Financial risk management method and device based on GBST and electronic equipment
CN111583014A
