Financial investment portfolio optimization method and system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent optimization combination of products. The financial portfolio optimization system comprises an investment association effect analysis module, a financial portfolio investment value analysis module, an investment risk analysis module and an investment portfolio rescreening and distribution module. The investment association effect analysis module analyzes association coefficients among the financial products and generates a financial product investment association chart; the financial portfolio investment value analysis module analyzes the overall investment value through the investment value of a single financial product and the correlation coefficient; the investment risk analysis module is used for judging whether the overall risk of the financial investment portfolio is increased or not by analyzing the whole investment portfolio; and the investment portfolio optimization module screens and distributes the financial investment portfolio again. According to the method, the overall risk of the investment portfolio is analyzed through the association effect between the financial products, and the investment portfolio is re-screened and distributed according to the association effect, so that the investment risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent product optimization combination, and specifically to a financial investment portfolio optimization method and system based on artificial intelligence. Background Art

[0002] As financial markets become increasingly complex, investors need to combine modern financial theories, quantitative tools and intelligent technologies to build robust portfolios that adapt to different market environments. A financial investment portfolio refers to investors or asset management institutions selecting financial products with complementary and operational value from stocks, bonds, insurance and funds based on specific investment objectives, risk preferences and market environment, and building a diversified asset pool through systematic allocation and dynamic management to achieve the goal of optimizing returns and reducing risks.

[0003] Under existing technologies, the correlation effect between financial products is the core factor that determines overall risk and acceptance. Ignoring this correlation may lead to a systemic collapse of the investment portfolio in extreme market environments, causing investors to suffer huge losses far beyond their expectations. Summary of the Invention

[0004] The purpose of the present invention is to provide a financial investment portfolio optimization method and system based on artificial intelligence to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a financial investment portfolio optimization method based on artificial intelligence, the financial investment portfolio optimization method specifically comprising the following steps:

[0006] Analyze the linkage effects between financial products based on their historical basic data and construct a financial product investment correlation effect diagram;

[0007] Analyze the investment value of individual products in the financial product library based on their historical basic data. Calculate the investment value of individual financial products based on the correlation coefficients between them. Use the financial product investment correlation effect diagram to identify financial products with correlation effects in the user's selected financial investment portfolio. Analyze the investment value of the financial products and the correlation coefficients between them to determine the overall investment value of the financial investment portfolio.

[0008] The initial investment value of the financial investment portfolio selected by the user is obtained through the investment value of a single financial product, and the investment risk of the financial investment portfolio is analyzed in combination with the overall investment value of the financial investment portfolio;

[0009] When the overall investment risk value of the financial investment portfolio selected by the user increases, an analysis is performed to determine whether the increased overall investment risk value of the financial investment portfolio falls within the user's risk tolerance range. When the increased overall investment risk value of the financial investment portfolio does not fall within the user's risk tolerance range, the financial products in the financial investment portfolio are ranked from high to low in terms of their impact on the overall investment value, and the products in the financial investment portfolio are eliminated and reallocated in order of their impact on the overall investment value.

[0010] Furthermore, the specific method for analyzing the linkage effect between financial products includes:

[0011] Select the historical basic data of two financial products, which are basic market data, including historical price data, trading volume data, volatility data and corresponding time nodes; calculate the average historical price of the financial product sc: It is represented by the average historical price of the selected financial product sc, R ct It is represented by the price of the financial product sc at time node t, t = 1, 2, 3...T, T represents the number of observation periods of the financial product, and T is a constant;

[0012] Through the covariance formula: To measure the degree of in-phase price changes between two financial products, Cov(R c , R v ) represents the linkage effect value between the two selected financial products sc and sv, E(R v ) represents the average historical price of the selected financial product sv, R vt It is expressed as the price of financial product sv at time node t. If Cov(R c , R v )=0, and the joint distribution obeys the multivariate normal distribution, then any two financial products selected are independent of each other;

[0013] Correlation coefficient between financial products: Calculate the correlation coefficient between any two financial products; P cv It is expressed as the correlation effect value between two randomly selected financial products sc and sv, P cv ∈[-1,1], when P cv =1, it indicates that there is a positive correlation between any two selected financial products; when P cv =-1, indicating that there is a complete negative correlation between any two selected financial products; σ c and σ v They are respectively expressed as the volatility of the prices of financial products sc and sv,

[0014] The correlation effects and correlation coefficients of the financial products in the financial product library are traversed, the financial products with correlation effect values not equal to zero in the financial product library are sorted out, and correlation links between the financial products are established to generate a financial product investment correlation chart. The financial product investment correlation effect chart includes the correlation links and correlation coefficients between the products in the financial product library. The larger the correlation effect value, the larger the correlation coefficient.

[0015] Furthermore, the specific method for analyzing the overall investment value of the financial investment group includes:

[0016] Based on the historical basic data of financial products, the investment value of each product in the financial product library is calculated: f i It is expressed as the investment value of the i-th product in the financial product library, E(R i ) is the average historical price of the i-th product in the financial product library, R it is the price of the i-th product in the financial product library at time node t; g it is the trading volume of the i-th product in the financial product library at time node t, where i = 1, 2, 3, ..., I, where I represents the number of products in the financial product library. When the historical value data of a financial product is proportional to the trading volume, it means that the trading volume is increasing as the purchase value increases, and the investment value of the financial product is high. Conversely, when the historical value data of a financial product is inversely proportional to the trading volume, it indicates that the investment value of the financial product is low.

[0017] The user selects a financial product sn corresponding to the financial investment portfolio S, where n = 1, 2, 3...N, where N represents the number of products in the user-selected financial investment portfolio, and N ≥ 2. Based on the financial product investment correlation effect chart, a set of products having correlation links with the financial product sn is extracted, namely Sn. The set of products in the financial product investment portfolio that have correlation links with the financial product sn is calculated as: Ln = S ∩ Sn, where Ln represents the set of products that have correlation links between the financial product sn and the user-selected financial product investment portfolio. Based on the financial product investment correlation effect chart, the financial products in the user-selected financial investment portfolio that have correlation links can be screened, thereby further completing the overall risk analysis of the user-selected financial investment portfolio.

[0018] According to the chart of financial product investment correlation effect, the investment value of financial products and the correlation coefficient of financial products in the set Ln are extracted as f nz 、P nz , according to the formula: Calculate the overall investment value of the financial investment portfolio S selected by the user; F' is the overall investment value of the financial investment portfolio selected by the user, f n The investment value of the nth product in the user's selected financial portfolio, f nz is the investment value of the zth product in the portfolio that has an associated link between the financial product sn and the portfolio, P nz is the correlation coefficient between the financial product sn and the zth product in the investment portfolio, z∈{1, 2, 3...N}, z≠n.

[0019] Furthermore, the specific method for determining whether the overall investment risk of the financial investment portfolio selected by the user has increased includes:

[0020] Based on the overall investment value F' of the financial portfolio S, the investment risk of the financial portfolio is calculated as: q = F - F', where q is the overall investment risk value of the financial portfolio selected by the user, and F represents the initial investment value of the financial portfolio S selected by the user, that is, the initial investment value of the financial portfolio when the user invests in financial products without considering the correlation effect between products.

[0021] When the overall risk value q of the financial investment portfolio selected by the user is less than the preset investment risk threshold Q, the overall risk value of the financial investment portfolio is determined to be stable, the financial investment portfolio is marked and recorded in the financial investment portfolio library; conversely, the overall risk value of the financial investment portfolio is determined to have increased, and the portfolio risk increase value is (qQ). The investor's risk questionnaire is obtained to determine the loss tolerance, i.e., the risk tolerance, and whether the portfolio risk increase value is within the user's loss tolerance range is determined based on the user's investment period. When the overall investment risk value of the financial investment portfolio increases and does not fall within the user's risk tolerance range, the financial investment portfolio selected by the user is re-screened and re-allocated.

[0022] Furthermore, the specific method of re-screening and re-allocating the financial investment portfolio selected by the user includes:

[0023] According to the product set Ln with associated links among the financial products in the financial investment portfolio selected by the user, the financial products in the financial investment portfolio are sorted according to Sort from high to low to get the overall investment value impact ranking. Since there are negative numbers in the correlation coefficient, it is necessary to calculate the correlation coefficient P of the financial products in the set Ln. nzBy summing absolute values, the financial products with the greatest impact on the overall investment value of the user's selected financial investment portfolio S can be calculated. Financial products in the financial product library that do not have associated links with the financial products in the financial investment group are traversed to generate a set U. Products in the financial investment portfolio are eliminated in order of their overall investment value impact, and the investment values of the financial products in set U are redistributed from high to low until the overall investment risk of the financial investment portfolio stabilizes after redistribution.

[0024] When there is no financial product in the financial product library that has no associated links with the financial products in the financial investment portfolio, according to the formula: Calculate the recommended value of financial products in the financial product library that have an associated link with the financial investment portfolio, and obtain the recommended value of financial products that are redistributed between the financial product library and the financial investment portfolio, D b The recommended value for the bth financial product to be reallocated with the financial investment portfolio in the financial product library, f b is the investment value of the bth financial product in the financial product library, P nb Expressed as the correlation coefficient between the bth financial product in the financial product library and financial product sn; products in the financial investment portfolio are eliminated in order of their overall investment value impact and reallocated from high to low according to the recommended value of the financial products until the overall investment risk of the allocated financial investment portfolio is stabilized; if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation combination, an alarm reminder will be issued.

[0025] An artificial intelligence-based financial investment portfolio optimization system, comprising an investment correlation effect analysis module, a financial portfolio investment value analysis module, an investment risk analysis module, and an investment portfolio re-screening and allocation module;

[0026] The investment correlation effect analysis module is used to select the historical basic data of any two financial products, analyze the historical prices of the financial products and the degree of in-phase price changes between the products, and obtain the correlation coefficient between the financial products; traverse the correlation effects and correlation coefficients of the financial products in the financial product library, sort out the financial products with non-zero correlation effects, build correlation links between the financial products, and generate a financial product investment correlation chart;

[0027] The financial portfolio investment value analysis module is used to analyze the investment value of individual products in the financial product library and the financial products with associated links in the user's selected financial portfolio, extract the correlation coefficients between the financial products in the user's selected financial portfolio based on the financial product investment association effect chart, and obtain the overall investment value of the user's selected financial portfolio;

[0028] The investment risk analysis module is used to analyze the overall investment value and initial investment value of the financial investment portfolio selected by the user to obtain the overall investment risk of the financial investment portfolio, and determine whether the overall risk of the financial investment portfolio has increased based on the overall investment risk;

[0029] The investment portfolio optimization module is configured to sort the financial products in the financial investment portfolio from high to low based on their impact on overall investment value, and traverse the products in the financial product library that have no associated links with the financial investment portfolio to generate a set U; sequentially eliminate products in the financial investment portfolio based on the ranking of their overall investment value impact, and redistribute the financial products in set U from high to low based on their investment value; when the financial product library does not contain any financial products that have no associated links with the financial products in the financial investment portfolio, analyze the recommended value of the financial products in the financial product library, and redistribute the financial products from high to low based on their recommended value; and issue an alarm if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation combination.

[0030] Furthermore, the investment correlation effect analysis module includes a linkage effect analysis unit, a correlation coefficient analysis unit and a link building and chart generation unit; the linkage effect analysis unit is used to analyze the average historical price of financial products through the historical basic data of any two financial products, and obtain the linkage effect value between financial products through the average historical price of financial products and price analysis at different time nodes; the correlation coefficient analysis unit is used to analyze the correlation coefficient through the linkage effect value between financial products; the link building and chart generation unit is used to sort out financial products in the financial product library whose correlation effect values are not zero, and build correlation links between financial products to generate a financial product investment correlation chart.

[0031] Furthermore, the financial portfolio investment value analysis module includes a product investment value analysis unit and a portfolio investment value analysis unit; the product investment value analysis unit is used to analyze the investment value of a single product in the financial product library through the historical value and trading volume of the financial product. When the historical value data of the financial product is proportional to the trading volume, the investment value of the financial product is large; when the investment value of the financial product is small, the investment value of the financial product is small; the portfolio investment value analysis unit is used to analyze the products with associated links in the financial investment portfolio through the financial product investment correlation effect chart, and obtain the overall investment value of the financial investment portfolio based on the correlation coefficient.

[0032] Furthermore, the investment portfolio optimization module includes an investment value impact analysis unit, a product recommendation value analysis unit and a combination optimization unit; the investment value impact analysis unit is used to obtain the impact of financial products in the financial investment portfolio on the overall investment value by performing an absolute value sum analysis of the correlation coefficients between products in the financial investment portfolio; the product recommendation value analysis unit is used to obtain the recommended value of products in the product library by using the product investment value and the correlation coefficient analysis when there are no financial products in the financial product library that have no correlation links with the financial products in the financial investment portfolio; the combination optimization unit is used to eliminate products in the financial investment portfolio in order according to the overall investment value impact ranking and reallocate and combine the products in the financial products from high to low according to the investment value or recommendation value, until the overall investment risk of the allocated financial investment portfolio is stabilized; if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening and allocating the combinations, an alarm reminder is issued.

[0033] Compared with the existing technology, the beneficial effects achieved by the present invention are as follows: the present invention traverses the correlation effects of financial products in the financial product library, and builds correlation links for financial products with correlation effects to generate a financial product investment correlation chart; the present invention analyzes and judges the overall risk of the financial investment portfolio based on the financial investment portfolio selected by the user, and re-screens and allocates the investment portfolio based on the correlation effects, thereby reducing investment risks and avoiding excessive risk concentration. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 The present invention is a flowchart of the steps of a financial investment portfolio optimization method based on artificial intelligence. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] See also Figure 1 The present invention provides a technical solution: a financial investment portfolio optimization method based on artificial intelligence, the financial investment portfolio optimization method specifically comprising the following steps:

[0038] Analyze the linkage effects between financial products based on their historical basic data and construct a financial product investment correlation effect diagram;

[0039] Analyze the investment value of individual products in the financial product library based on their historical basic data. Calculate the investment value of individual financial products based on the correlation coefficients between them. Use the financial product investment correlation effect diagram to identify financial products with correlation effects in the user's selected financial investment portfolio. Analyze the investment value of the financial products and the correlation coefficients between them to determine the overall investment value of the financial investment portfolio.

[0040] The initial investment value of the financial investment portfolio selected by the user is obtained through the investment value of a single financial product, and the investment risk of the financial investment portfolio is analyzed in combination with the overall investment value of the financial investment portfolio;

[0041] When the overall investment risk value of the financial investment portfolio selected by the user increases, an analysis is performed to determine whether the increased overall investment risk value of the financial investment portfolio falls within the user's risk tolerance range. When the increased overall investment risk value of the financial investment portfolio does not fall within the user's risk tolerance range, the financial products in the financial investment portfolio are ranked from high to low in terms of their impact on the overall investment value, and the products in the financial investment portfolio are eliminated and reallocated in order of their impact on the overall investment value.

[0042] Furthermore, the specific method for analyzing the linkage effect between financial products includes:

[0043] Select the historical basic data of two financial products, which are basic market data, including historical price data, trading volume data, volatility data and corresponding time nodes; calculate the average historical price of the financial product sc: E(R c ) represents the average historical price of the selected financial product sc, R ct It is represented by the price of the financial product sc at time node t, t = 1, 2, 3...T, T represents the number of observation periods of the financial product, and T is a constant;

[0044] Through the covariance formula: To measure the degree of in-phase price changes between two financial products, Cov(R c , R v ) represents the linkage effect value between the two selected financial products sc and sv, E(R v ) represents the average historical price of the selected financial product sv, R vt It is expressed as the price of financial product sv at time node t. If Cov(R c , Rv )=0, and the joint distribution obeys the multivariate normal distribution, then any two financial products selected are independent of each other;

[0045] Correlation coefficient between financial products: Calculate the correlation coefficient between any two financial products; P cv It is expressed as the correlation effect value between two randomly selected financial products sc and sv, P cv ∈[-1,1], when P cv =1, it indicates that there is a positive correlation between any two selected financial products; when P cv =-1, indicating that there is a complete negative correlation between any two selected financial products; σ c and σ v They are respectively expressed as the volatility of the prices of financial products sc and sv,

[0046] The correlation effects and correlation coefficients of the financial products in the financial product library are traversed, the financial products with correlation effect values not equal to zero in the financial product library are sorted out, and correlation links between the financial products are established to generate a financial product investment correlation chart. The financial product investment correlation effect chart includes the correlation links and correlation coefficients between the products in the financial product library. The larger the correlation effect value, the larger the correlation coefficient.

[0047] Furthermore, the specific method for analyzing the overall investment value of the financial investment group includes:

[0048] Based on the historical basic data of financial products, the investment value of each product in the financial product library is calculated: f i It is expressed as the investment value of the i-th product in the financial product library, E(R i ) is the average historical price of the i-th product in the financial product library, R it is the price of the i-th product in the financial product library at time node t; g it is the trading volume of the i-th product in the financial product library at time node t, where i = 1, 2, 3, ..., I, where I represents the number of products in the financial product library. When the historical value data of a financial product is proportional to the trading volume, it means that the trading volume is increasing as the purchase value increases, and the investment value of the financial product is high. Conversely, when the historical value data of a financial product is inversely proportional to the trading volume, it indicates that the investment value of the financial product is low.

[0049] The user selects a financial product sn corresponding to the financial investment portfolio S, where n = 1, 2, 3...N, where N represents the number of products in the user-selected financial investment portfolio, and N ≥ 2. Based on the financial product investment correlation effect chart, a set of products having correlation links with the financial product sn is extracted, namely Sn. The set of products in the financial product investment portfolio that have correlation links with the financial product sn is calculated as: Ln = S ∩ Sn, where Ln represents the set of products that have correlation links between the financial product sn and the user-selected financial product investment portfolio. Based on the financial product investment correlation effect chart, the financial products in the user-selected financial investment portfolio that have correlation links can be screened, thereby further completing the overall risk analysis of the user-selected financial investment portfolio.

[0050] According to the chart of financial product investment correlation effect, the investment value of financial products and the correlation coefficient of financial products in the set Ln are extracted as f nz 、P nz , according to the formula: Calculate the overall investment value of the financial investment portfolio S selected by the user; F' is the overall investment value of the financial investment portfolio selected by the user, f n The investment value of the nth product in the user's selected financial portfolio, f nz is the investment value of the zth product in the portfolio that has an associated link between the financial product sn and the portfolio, P nz is the correlation coefficient between the financial product sn and the zth product in the investment portfolio, z∈{1, 2, 3...N}, z≠n.

[0051] Furthermore, the specific method for determining whether the overall investment risk of the financial investment portfolio selected by the user has increased includes:

[0052] Based on the overall investment value F' of the financial portfolio S, the investment risk of the financial portfolio is calculated as: q = F - F', where q is the overall investment risk value of the financial portfolio selected by the user, and F represents the initial investment value of the financial portfolio S selected by the user, that is, the initial investment value of the financial portfolio when the user invests in financial products without considering the correlation effect between products.

[0053] When the overall risk value q of the financial investment portfolio selected by the user is less than the preset investment risk threshold Q, the overall risk value of the financial investment portfolio is determined to be stable, the financial investment portfolio is marked and recorded in the financial investment portfolio library; conversely, the overall risk value of the financial investment portfolio is determined to have increased, and the portfolio risk increase value is (qQ). The investor's risk questionnaire is obtained to determine the loss tolerance, i.e., the risk tolerance, and whether the portfolio risk increase value is within the user's loss tolerance range is determined based on the user's investment period. When the overall investment risk value of the financial investment portfolio increases and does not fall within the user's risk tolerance range, the financial investment portfolio selected by the user is re-screened and re-allocated.

[0054] Furthermore, the specific method of re-screening and re-allocating the financial investment portfolio selected by the user includes:

[0055] According to the product set Ln with associated links among the financial products in the financial investment portfolio selected by the user, the financial products in the financial investment portfolio are sorted according to Sort from high to low to get the overall investment value impact ranking. Since there are negative numbers in the correlation coefficient, it is necessary to calculate the correlation coefficient P of the financial products in the set Ln. nz By summing absolute values, the financial products with the greatest impact on the overall investment value of the user's selected financial investment portfolio S can be calculated. Financial products in the financial product library that do not have associated links with the financial products in the financial investment group are traversed to generate a set U. Products in the financial investment portfolio are eliminated in order of their overall investment value impact, and the investment values of the financial products in set U are redistributed from high to low until the overall investment risk of the financial investment portfolio stabilizes after redistribution.

[0056] When there is no financial product in the financial product library that has no associated links with the financial products in the financial investment portfolio, according to the formula: Calculate the recommended value of financial products in the financial product library that have an associated link with the financial investment portfolio, and obtain the recommended value of financial products that are redistributed between the financial product library and the financial investment portfolio, D b The recommended value for the bth financial product to be reallocated with the financial investment portfolio in the financial product library, f b is the investment value of the bth financial product in the financial product library, P nb Expressed as the correlation coefficient between the bth financial product in the financial product library and financial product sn; products in the financial investment portfolio are eliminated in order of their overall investment value impact and reallocated from high to low according to the recommended value of the financial products until the overall investment risk of the allocated financial investment portfolio is stabilized; if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation combination, an alarm reminder will be issued.

[0057] An artificial intelligence-based financial investment portfolio optimization system, comprising an investment correlation effect analysis module, a financial portfolio investment value analysis module, an investment risk analysis module, and an investment portfolio re-screening and allocation module;

[0058] The investment correlation effect analysis module is used to select the historical basic data of any two financial products, analyze the historical prices of the financial products and the degree of in-phase price changes between the products, and obtain the correlation coefficient between the financial products; traverse the correlation effects and correlation coefficients of the financial products in the financial product library, sort out the financial products with non-zero correlation effects, build correlation links between the financial products, and generate a financial product investment correlation chart;

[0059] The financial portfolio investment value analysis module is used to analyze the investment value of individual products in the financial product library and the financial products with associated links in the user's selected financial portfolio, extract the correlation coefficients between the financial products in the user's selected financial portfolio based on the financial product investment association effect chart, and obtain the overall investment value of the user's selected financial portfolio;

[0060] The investment risk analysis module is used to analyze the overall investment value and initial investment value of the financial investment portfolio selected by the user to obtain the overall investment risk of the financial investment portfolio, and determine whether the overall risk of the financial investment portfolio has increased based on the overall investment risk;

[0061] The investment portfolio optimization module is configured to sort the financial products in the financial investment portfolio from high to low based on their impact on overall investment value, and traverse the products in the financial product library that have no associated links with the financial investment portfolio to generate a set U; sequentially eliminate products in the financial investment portfolio based on the ranking of their overall investment value impact, and redistribute the financial products in set U from high to low based on their investment value; when the financial product library does not contain any financial products that have no associated links with the financial products in the financial investment portfolio, analyze the recommended value of the financial products in the financial product library, and redistribute the financial products from high to low based on their recommended value; and issue an alarm if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation combination.

[0062] Furthermore, the investment correlation effect analysis module includes a linkage effect analysis unit, a correlation coefficient analysis unit and a link building and chart generation unit; the linkage effect analysis unit is used to analyze the average historical price of financial products through the historical basic data of any two financial products, and obtain the linkage effect value between financial products through the average historical price of financial products and price analysis at different time nodes; the correlation coefficient analysis unit is used to analyze the correlation coefficient through the linkage effect value between financial products; the link building and chart generation unit is used to sort out financial products in the financial product library whose correlation effect values are not zero, and build correlation links between financial products to generate a financial product investment correlation chart.

[0063] Furthermore, the financial portfolio investment value analysis module includes a product investment value analysis unit and a portfolio investment value analysis unit; the product investment value analysis unit is used to analyze the investment value of a single product in the financial product library through the historical value and trading volume of the financial product. When the historical value data of the financial product is proportional to the trading volume, the investment value of the financial product is large; when the investment value of the financial product is small, the investment value of the financial product is small; the portfolio investment value analysis unit is used to analyze the products with associated links in the financial investment portfolio through the financial product investment correlation effect chart, and obtain the overall investment value of the financial investment portfolio based on the correlation coefficient.

[0064] Furthermore, the investment portfolio optimization module includes an investment value impact analysis unit, a product recommendation value analysis unit and a combination optimization unit; the investment value impact analysis unit is used to obtain the impact of financial products in the financial investment portfolio on the overall investment value by performing an absolute value sum analysis of the correlation coefficients between products in the financial investment portfolio; the product recommendation value analysis unit is used to obtain the recommended value of products in the product library by using the product investment value and the correlation coefficient analysis when there are no financial products in the financial product library that have no correlation links with the financial products in the financial investment portfolio; the combination optimization unit is used to eliminate products in the financial investment portfolio in order according to the overall investment value impact ranking and reallocate and combine the products in the financial products from high to low according to the investment value or recommendation value, until the overall investment risk of the allocated financial investment portfolio is stabilized; if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening and allocating the combinations, an alarm reminder is issued.

[0065] In this embodiment:

[0066] The financial products with non-zero correlation effect values in the financial product library are sorted out, and correlation links between financial products are established to generate a financial product investment correlation chart. The financial product investment correlation effect chart includes the correlation links and correlation coefficients between each product in the financial product library. The larger the correlation effect value, the larger the correlation coefficient. Based on the historical basic data of financial products, according to the formula: Calculate the investment value f of a single product in the financial product library i = {78, 63, 90...}; the user selects the corresponding financial product sn in the financial investment portfolio S, where N ≥ 2; based on the financial product investment correlation effect chart, the product sets associated with the financial product sn are extracted, each of which is Sn. The set of products associated with the financial product sn in the financial product investment portfolio is calculated as: Ln = S ∩ Sn, where Ln represents the set of products associated with the financial product sn and the user-selected financial product investment portfolio.

[0067] Example 1: Based on the financial product investment correlation effect chart, the investment value of the financial products in the set Ln and the correlation coefficient of the financial products are extracted respectively as f nz 、P nz , according to the formula: Calculate the overall investment value of the user's selected financial investment portfolio S;

[0068] According to the overall investment value F' of the financial investment portfolio S, the investment risk of the financial investment portfolio is calculated as follows: q = F-F' = 13,

[0069] If the overall risk value q of the financial investment portfolio selected by the user is less than the preset investment risk threshold Q=15, the overall risk value of the financial investment portfolio is determined to be stable, the financial investment portfolio is marked and recorded in the financial investment portfolio database;

[0070] Example 2: Based on the financial product investment correlation effect chart, the investment value of the financial products in the set Ln and the correlation coefficient of the financial products are extracted respectively as f nz 、P nz , according to the formula: Calculate the overall investment value of the user's selected financial investment portfolio S;

[0071] According to the overall investment value F' of the financial investment portfolio S, the investment risk of the financial investment portfolio is calculated as follows: q = F-F' = 27,

[0072] If the overall risk value q of the financial investment portfolio selected by the user exceeds the preset investment risk threshold Q=15, the overall risk value of the financial investment portfolio is determined to be stable, the financial investment portfolio is marked and recorded in the financial investment portfolio database;

[0073] If the overall risk value of the financial investment portfolio is determined to have increased, the financial investment portfolio selected by the user will be rescreened and allocated.

[0074] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0075] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A financial investment portfolio optimization method based on artificial intelligence, characterized by: The financial investment portfolio optimization method specifically includes the following steps: Analyze the linkage effects between financial products based on their historical basic data and construct a financial product investment correlation effect diagram; Calculate the investment value of a single financial product based on the correlation coefficient between them. Identify the financial products with correlation effects in the user's selected financial portfolio based on the financial product investment correlation effect diagram. Analyze the investment value of the financial products and the correlation coefficients between them to determine the overall investment value of the financial portfolio. The initial investment value of the financial investment portfolio selected by the user is obtained through the investment value of a single financial product, and the investment risk of the financial investment portfolio is analyzed in combination with the overall investment value of the financial investment portfolio; When the overall investment risk value of the financial investment portfolio selected by the user increases, the products in the financial investment portfolio will be eliminated and reallocated in order of their impact on the overall investment value.

2. The artificial intelligence-based financial investment portfolio optimization method according to claim 1, characterized in that: The specific methods for analyzing the linkage effects between financial products include: Select the historical basic data of two financial products, which are basic market data, including historical price data, trading volume data, volatility data and corresponding time nodes; calculate the average historical price of the financial product sc: E(R c ) represents the average historical price of the selected financial product sc, R ct It is represented by the price of the financial product sc at time node t, t = 1, 2, 3...T, T represents the number of observation periods of the financial product, and T is a constant; By formula: To measure the degree of in-phase price changes between two financial products, Cov(R c , R v ) represents the linkage effect value between the two selected financial products sc and sv, E(R v ) represents the average historical price of the selected financial product sv, R vt It is represented by the price of financial product sv at time node t; Correlation coefficient between financial products: Calculate the correlation coefficient between any two financial products; P cv It is expressed as the correlation effect value between two randomly selected financial products sc and sv, P cv ∈[-1,1],σ c and σ v They are respectively expressed as the volatility of the prices of financial products sc and sv; The correlation effects and correlation coefficients of the financial products in the financial product library are traversed, the financial products with correlation effect values not equal to zero in the financial product library are sorted out, and correlation links between the financial products are established to generate a financial product investment correlation chart. The financial product investment correlation effect chart includes the correlation links and correlation coefficients between the products in the financial product library.

3. The artificial intelligence-based financial investment portfolio optimization method according to claim 2, characterized in that: The specific method for analyzing the overall investment value of the financial investment group includes: Based on the historical basic data of financial products, the investment value of each product in the financial product library is calculated: f i It is expressed as the investment value of the i-th product in the financial product library, E(R i ) is the average historical price of the i-th product in the financial product library, R it is the price of the i-th product in the financial product library at time node t; g it is the trading volume of the i-th product in the financial product library at time node t, i = 1, 2, 3...I, where I represents the number of products in the financial product library; The user selects a financial product sn corresponding to the financial investment portfolio S, where n = 1, 2, 3...N, where N represents the number of products in the user's selected financial investment portfolio and N ≥ 2; based on the financial product investment correlation effect chart, the product sets that have correlation links with the financial product sn are extracted, and are respectively Sn. The set of products in the financial product investment portfolio that have correlation links with the financial product sn is calculated: Ln = S ∩ Sn, where Ln represents the set of products that have correlation links with the financial product sn and the user's selected financial product investment portfolio; According to the chart of financial product investment correlation effect, the investment value of financial products and the correlation coefficient of financial products in the set Ln are extracted as f nz 、P nz , according to the formula: Calculate the overall investment value of the financial investment portfolio S selected by the user; F' is the overall investment value of the financial investment portfolio selected by the user, f n The investment value of the nth product in the user's selected financial portfolio, f nz is the investment value of the zth product in the portfolio that has an associated link between the financial product sn and the portfolio, P nz is the correlation coefficient between the financial product sn and the zth product in the investment portfolio, z∈{1, 2, 3...N}, z≠n.

4. The artificial intelligence-based financial investment portfolio optimization method according to claim 3, characterized in that: The specific method for determining whether the overall investment risk of the financial investment portfolio selected by the user has increased includes: According to the overall investment value F' of the financial investment portfolio S, the investment risk of the financial investment portfolio is calculated as follows: q = F - F', where q is the overall investment risk value of the financial investment portfolio selected by the user, and F represents the initial investment value of the financial investment portfolio S selected by the user. When the overall risk value q of the financial investment portfolio selected by the user is less than the preset investment risk threshold, the overall risk value of the financial investment portfolio is determined to be stable; otherwise, the overall risk value of the financial investment portfolio is determined to have increased, and the financial investment portfolio selected by the user is re-screened and allocated.

5. The artificial intelligence-based financial investment portfolio optimization method according to claim 4, characterized in that: The specific method of re-screening and re-allocating the financial investment portfolio selected by the user includes: According to the product set Ln with associated links among the financial products in the financial investment portfolio selected by the user, the financial products in the financial investment portfolio are sorted according to Sort from high to low to obtain the overall investment value impact ranking; traverse the financial products in the financial product library that have no associated links with the financial products in the financial investment portfolio to generate a set U, and eliminate the products in the financial investment portfolio in order according to the overall investment value impact ranking. Then, redistribute the investment value of the financial products in set U from high to low until the overall investment risk of the financial investment portfolio after redistribution is stabilized; When there is no financial product in the financial product library that has no associated links with the financial products in the financial investment portfolio, according to the formula: Calculate the recommended value of financial products in the financial product library that have an associated link with the financial investment portfolio, and obtain the recommended value of financial products that are redistributed between the financial product library and the financial investment portfolio, D b The recommended value for the bth financial product to be reallocated with the financial investment portfolio in the financial product library, f b is the investment value of the bth financial product in the financial product library, P nb Expressed as the correlation coefficient between the bth financial product in the financial product library and financial product sn; products in the financial investment portfolio are eliminated in order of their overall investment value impact and reallocated from high to low according to the recommended value of the financial products until the overall investment risk of the allocated financial investment portfolio is stabilized; if the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation combination, an alarm reminder will be issued.

6. An artificial intelligence-based financial investment portfolio optimization system, characterized by: The financial investment portfolio optimization system includes an investment correlation effect analysis module, a financial portfolio investment value analysis module, an investment risk analysis module and an investment portfolio re-screening and allocation module; The investment correlation effect analysis module is used to select the historical basic data of any two financial products, analyze the historical prices of the financial products and the degree of in-phase price changes between the products, and obtain the correlation coefficient between the financial products; traverse the correlation effects and correlation coefficients of the financial products in the financial product library, sort out the financial products with non-zero correlation effects, build correlation links between the financial products, and generate a financial product investment correlation chart; The financial portfolio investment value analysis module is used to analyze the investment value of individual products in the financial product library and the financial products with associated links in the user's selected financial portfolio, extract the correlation coefficients between the financial products in the user's selected financial portfolio based on the financial product investment association effect chart, and obtain the overall investment value of the user's selected financial portfolio; The investment risk analysis module is used to analyze the overall investment value and initial investment value of the financial investment portfolio selected by the user to obtain the overall investment risk of the financial investment portfolio, and determine whether the overall risk of the financial investment portfolio has increased based on the overall investment risk; The investment portfolio optimization module is configured to sort the financial products in the financial investment portfolio from high to low based on their impact on overall investment value, and traverse the products in the financial product library that have no associated links with the financial investment portfolio to generate a set U; sequentially remove products from the financial investment portfolio based on the ranking of overall investment value impact, and redistribute the financial products in set U from high to low based on their investment value; and when there are no financial products in the financial product library that have no associated links with the financial products in the financial investment portfolio, analyze the recommended value of the financial products in the financial product library and redistribute the financial products from high to low based on their recommended value; If the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation portfolio, an alarm reminder will be issued.

7. The artificial intelligence-based financial investment portfolio optimization system according to claim 6, characterized in that: The investment correlation effect analysis module includes a linkage effect analysis unit, a correlation coefficient analysis unit, and a link building and chart generation unit; the linkage effect analysis unit is used to analyze the average historical price of any two financial products based on the historical basic data of the financial products, and obtain the linkage effect value between the financial products through the average historical price of the financial products and the price analysis at different time nodes; the correlation coefficient analysis unit is used to analyze the correlation coefficient based on the linkage effect value between the financial products; the link building and chart generation unit is used to sort out the financial products in the financial product library whose correlation effect values are not zero, and build correlation links between the financial products to generate a financial product investment correlation chart.

8. The artificial intelligence-based financial investment portfolio optimization system according to claim 7, characterized in that: The financial portfolio investment value analysis module includes a product investment value analysis unit and a portfolio investment value analysis unit; the product investment value analysis unit is used to analyze the investment value of a single product in the financial product library based on the historical value and trading volume of the financial product. When the historical value data of a financial product is proportional to the trading volume, the investment value of the financial product is large; when the investment value of the financial product is small, the investment value of the financial product is small; the portfolio investment value analysis unit is used to analyze products with associated links in the financial investment portfolio through a financial product investment association effect chart, and obtain the overall investment value of the financial investment portfolio based on the association coefficient.

9. The artificial intelligence-based financial investment portfolio optimization system according to claim 8, characterized in that: The investment portfolio optimization module includes an investment value impact analysis unit, a product recommendation value analysis unit, and a combination optimization unit; the investment value impact analysis unit is configured to obtain the impact of financial products in the financial portfolio on the overall investment value by summing the absolute values of correlation coefficients between products in the financial portfolio; the product recommendation value analysis unit is configured to obtain the recommended value of products in the product library by using the product investment value and correlation coefficient analysis when there are no financial products in the financial product library that are not associated with the financial products in the financial portfolio; the combination optimization unit is configured to sequentially eliminate products in the financial portfolio based on the ranking of overall investment value impact and reallocate and combine the products in the financial portfolio according to their investment value or recommendation value from high to low until the overall investment risk of the allocated financial portfolio is stabilized; If the overall investment risk of the allocated financial investment portfolio cannot be stabilized by re-screening the allocation portfolio, an alarm reminder will be issued.

Images