Investment portfolio optimization strategy generation method and device, equipment, medium and product

Abstract

The invention discloses a portfolio optimization strategy generation method, device and equipment, a medium and a product. The method can be applied to the field of financial science and technology, and comprises the steps: determining the expected yield of a target product of at least one target enterprise; determining risk coefficients among the target enterprises according to the expected yield rates of the target products of the target enterprises; determining an optimization strategy of the target portfolio according to the expected return rate of the target product of each target enterprise and based on the risk coefficient between the target enterprises; the optimization strategy of the target investment portfolio comprises resource allocation shares of target products of the target enterprises. According to the technical scheme of the embodiment of the invention, automatic generation of the optimization strategy of the portfolio is realized, and the generation efficiency and the generation accuracy of the optimization strategy of the portfolio are improved.

Description

Technical Field

[0001] This invention relates to the field of financial technology, and in particular to a method, apparatus, device, medium and product for generating portfolio optimization strategies. Background Technology

[0002] Optimizing an investment portfolio involves selecting specific corporate investment products and allocating resources to each product to meet the specific needs of specific individuals.

[0003] Existing methods for generating portfolio optimization strategies typically involve manual configuration by technical personnel based on the expected rate of return of the company's investment products; or the generation of several possible portfolio options using a random combination algorithm, from which a set that meets specific requirements is selected. However, these methods are inefficient and susceptible to subjective human factors, resulting in low accuracy and an inability to meet the specific needs of particular personnel. Summary of the Invention

[0004] This invention provides a method, apparatus, device, medium, and product for generating portfolio optimization strategies, so as to realize the automatic generation of portfolio optimization strategies and improve the efficiency and accuracy of portfolio optimization strategy generation.

[0005] According to one aspect of the present invention, a method for generating an optimization strategy for an investment portfolio is provided, the method comprising:

[0006] Determine the expected rate of return for the target product of at least one target company;

[0007] Based on the expected rate of return of the target products of each target company, determine the risk coefficient among the target companies;

[0008] Based on the expected rate of return of the target products of each target enterprise and the risk coefficients among the target enterprises, an optimization strategy for the target portfolio is determined; the optimization strategy for the target portfolio includes the resource allocation share of the target products of each target enterprise.

[0009] According to another aspect of the present invention, an apparatus for generating portfolio optimization strategies is provided, the apparatus comprising:

[0010] The expected rate of return determination module is used to determine the expected rate of return of a target product of at least one target enterprise.

[0011] The risk coefficient determination module is used to determine the risk coefficient between the target companies based on the expected rate of return of the target products of each target company.

[0012] The optimization strategy generation module is used to determine the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between each target enterprise; the optimization strategy of the target portfolio includes the resource allocation share of the target products of each target enterprise.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the portfolio optimization strategy generation method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the portfolio optimization strategy generation method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the portfolio optimization strategy generation method described in any embodiment of the present invention.

[0019] The technical solution of this invention determines the expected rate of return of the target product of at least one target enterprise, determines the risk coefficient between the target enterprises based on the expected rate of return of the target products of each target enterprise, and determines the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between the target enterprises. The technical solution of this invention realizes the automated determination of the optimization strategy of the target portfolio, improves the generation efficiency of the optimization strategy of the portfolio, and improves the accuracy of the generation of the optimization strategy of the portfolio by comprehensively considering the expected rate of return of the target products and the risk coefficient between enterprises in the process of determining the optimization strategy.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a portfolio optimization strategy generation method according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a method for generating an optimization strategy for an investment portfolio according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a flowchart of a portfolio optimization strategy generation method provided in Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an portfolio optimization strategy generation device according to Embodiment 4 of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the portfolio optimization strategy generation method of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart illustrating a method for generating an investment portfolio optimization strategy according to Embodiment 1 of the present invention. This embodiment is applicable to generating optimization strategies for investment portfolios that meet the specific needs of specific individuals for corporate investment products. This method can be executed by an investment portfolio optimization strategy generation device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110. Determine the expected rate of return of at least one target company's target product.

[0032] S120. Determine the risk coefficients among the target companies based on the expected rate of return of their target products.

[0033] S130. Based on the expected rate of return of the target products of each target enterprise and the risk coefficients among the target enterprises, determine the optimization strategy of the target portfolio; the optimization strategy of the target portfolio includes the resource allocation share of the target products of each target enterprise.

[0034] The target product of the target company can be an investment product of the company; the expected rate of return of the target product of the target company is publicly available data of the target company and can be directly obtained. Alternatively, the expected rate of return of the target product of the target company can also be determined based on the historical return information of the target product publicly available by the target company over a historical period; specifically, the expected rate of return of the target product of the target company can be determined based on historical return information and the publicly available data of the target company, and on expert experience.

[0035] It should be noted that the information or data collected regarding the expected rate of return and historical earnings of the target companies mentioned above are information and data authorized by the companies or relevant personnel or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of such data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for companies or relevant personnel to choose to authorize or refuse.

[0036] The risk coefficients among the target companies are used to characterize the correlation between the returns of different companies. These risk coefficients can be represented using a risk coefficient matrix. Specifically, the expected returns of the target companies at different periods are obtained. Based on these expected returns and a pre-defined covariance matrix calculation function, a risk coefficient matrix is ​​determined to characterize the risk coefficients among the target companies.

[0037] For example, if the number of target companies is N, then the size of the constructed risk coefficient matrix will be N*N, where N... ij This indicates the correlation or degree of correlation between target company i and target company j.

[0038] The optimization strategy for the target portfolio involves allocating the target resources of a specific individual to the resource allocation share of the target products of each target enterprise. For example, if the target resources of individual A are M, and the target products include product a, product b, and product c, the optimization strategy for a given portfolio is to allocate resource A to product a, resource B to product b, and resource C to product c; where the sum of resources A, B, and C is the target resource M.

[0039] For example, the optimization strategy for the target portfolio can be determined based on the expected rate of return and risk coefficient of the target products of each target company. The target optimization function F is constructed as follows:

[0040] F=u*w-γw T ∑w;

[0041] Where u represents the expected rate of return of the target company's target product, for example, u = [u1, u2, ..., u] i ,…,u n ] T , where u i Let w represent the expected rate of return of the target product of the i-th target company. w represents the target investment portfolio to be evaluated, for example, w = [w1, w2, ..., w...]. i ,…,w n ] T , where w i γ represents the resource allocation share from the target resources allocated to the i-th target product; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs. The larger its value, the greater the impact of risk-related considerations on the final mean-variance analysis value, indicating that the optimization strategy tends to be conservative and requires more consideration of risk; ∑ represents the risk coefficient between each target enterprise.

[0042] Where u*w represents the current portfolio rate of return; w T ∑w represents the expected risk of the current portfolio; F represents the expected return and risk of the current portfolio w, and the larger the value, the better the portfolio.

[0043] Therefore, we can randomly iterate through the optimization strategies of several portfolios and calculate the objective function value F based on the above objective optimization function, and take the portfolio with the largest objective function value F as the optimization strategy of the target portfolio.

[0044] The technical solution of this invention determines the expected rate of return of the target product of at least one target enterprise, determines the risk coefficient between the target enterprises based on the expected rate of return of the target products of each target enterprise, and determines the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between the target enterprises. The technical solution of this invention realizes the automated determination of the optimization strategy of the target portfolio, improves the generation efficiency of the optimization strategy of the portfolio, and improves the accuracy of the generation of the optimization strategy of the portfolio by comprehensively considering the expected rate of return of the target products and the risk coefficient between enterprises in the process of determining the optimization strategy.

[0045] Example 2

[0046] Figure 2 This is a flowchart of a method for generating an optimization strategy for an investment portfolio according to Embodiment 2 of the present invention. This embodiment is an optimization and improvement based on the above-mentioned technical solutions.

[0047] Furthermore, the step "determine the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target company and the risk coefficient between each target company" is refined into "if the current iteration period is not the first iteration and the current cycle period is not the first cycle, then obtain the historical portfolio strategy of the previous cycle under the current iteration period; the historical portfolio strategy includes a first historical strategy and a second historical strategy; generate a first current strategy based on the first historical strategy, and generate a second current strategy based on the second historical strategy; generate a first target strategy based on the first current strategy and the first historical strategy, based on the expected rate of return of the target products of each target company and the risk coefficient of each target company, and generate a second target strategy based on the second current strategy and the second historical strategy, based on the expected rate of return of the target products of each target company and the risk coefficient of each target company; if the current iteration period meets the preset iteration end condition and the current cycle period meets the preset cycle end condition, then determine the optimization strategy of the target portfolio based on the first target strategy and the second target strategy." This improves the method for determining the optimization strategy of the target portfolio.

[0048] It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments. For example... Figure 2 As shown, the method includes the following specific steps:

[0049] S210. Determine the expected rate of return of at least one target company's target product.

[0050] S220. Determine the risk coefficients among the target companies based on the expected rate of return of their target products.

[0051] S230. If the current iteration period is not the first iteration and the current cycle period is not the first cycle, then obtain the historical combination strategy of the previous cycle period under the current iteration period; the historical combination strategy includes the first historical strategy and the second historical strategy.

[0052] S240. Generate a first current strategy based on the first historical strategy, and generate a second current strategy based on the second historical strategy.

[0053] S250. Based on the first current strategy and the first historical strategy, generate a first target strategy based on the expected rate of return of the target products of each target company and the risk coefficient of each target company in the past; and based on the second current strategy and the second historical strategy, generate a second target strategy based on the expected rate of return of the target products of each target company and the risk coefficient of each target company in the past.

[0054] S260. If the current iteration period meets the preset iteration termination condition and the current cycle period meets the preset cycle termination condition, then the optimization strategy of the target portfolio is determined according to the first target strategy and the second target strategy.

[0055] The iteration cycle and the cycle period can be preset by relevant technical personnel according to actual needs. For example, the iteration cycle can be set to 100 times and the cycle period can be set to 50 times.

[0056] In any iteration cycle, the entire loop cycle must be executed. For example, for the 20th iteration, the loop cycle needs to be executed 50 times in this iteration cycle.

[0057] Taking any iteration cycle as an example, and considering that the iteration cycle is not the first iteration, and the cycle under the iteration cycle is not the first cycle, we will use the iteration cycle and the cycle as the current iteration cycle and the current cycle as examples to illustrate.

[0058] Obtain the historical combination strategy from the previous iteration cycle under the current iteration cycle; where the historical combination strategy includes the first historical strategy and the second historical strategy. For example, if the current iteration cycle is the 20th iteration and the current cycle cycle is the 10th cycle, then the previous cycle cycle is the 9th cycle cycle under the 20th iteration cycle.

[0059] Both the first and second historical strategies are possible combinations of the transaction sequences to be identified determined in the previous cycle. For example, the historical strategy could be [3000, 4000, 6000, 2000]. Based on a preset neighborhood function, a first current strategy is obtained. The neighborhood function is used to randomly change the value of a position in a vector using a random number, thus generating several different combinations of the first historical strategy. For example, if the first historical strategy is [3000, 4000, 6000, 2000], then the first current strategy randomly generated based on the preset neighborhood function could be [4000, 3000, 2000, 6000]. The second current strategy is generated similarly, based on the preset neighborhood function and the second historical strategy. For example, if the second historical strategy is [2000, 5000, 3000, 4000], then the first current strategy randomly generated based on the preset neighborhood function could be [3000, 5000, 2000, 4000].

[0060] It should be noted that, under given constraints, the generated strategies must satisfy those constraints. For example, if the constraint is a target resource of 10,000, then the sum of the share percentages in the generated combined strategies must equal the target resource. For instance, if the target resource is set to 10,000, the first historical strategy generated would be [3000, 4000, 2000, 1000]. The first current strategy randomly generated based on a preset domain function could be [3000, 1000, 4000, 2000]. The sum of the share percentages in the strategies would equal the target resource.

[0061] In an optional embodiment, a first target strategy is generated based on a first current strategy and a first historical strategy, taking into account the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past; and a second target strategy is generated based on a second current strategy and a second historical strategy, taking into account the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past, including:

[0062] Step a1: Obtain the objective function value of the first historical strategy and the objective function value of the second historical strategy.

[0063] The objective function values ​​for the first and second historical strategies are calculated based on a preset optimization function in the previous iteration cycle. The calculation method for the objective function value is the same for any iteration cycle. Steps a21 and a22 will be explained in detail using the objective function value at the current iteration number as an example.

[0064] Step a21: Based on the first current strategy, the expected rate of return of the target products of each target company, and the previous risk coefficient of each target company, determine the objective function value of the first current strategy based on the objective function value of the second historical strategy; determine the first target strategy based on the objective function value of the first current strategy and the objective function value of the first historical strategy.

[0065] For example, let's set the current loop cycle as the Nth iteration, and the preset objective optimization function is expressed as follows:

[0066]

[0067] Among them, F N (σ N ) represents the objective function value of the first current strategy in the Nth iteration; σ N For the first current strategy, u is the expected rate of return matrix of the target products of each target enterprise; η represents the momentum coupling parameter, which can be preset by relevant technical personnel according to actual needs, with a value range of [0,1]. Preferably, η can be set to 0.2. F N-1 (τ N-1 ) represents the objective function value of the second historical strategy in the N-1th cycle, i.e. the previous cycle; ∑ represents the risk coefficient between each target enterprise; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs.

[0068] Among them, u, σ N and τ N-1 All are n*1 matrices, for example, u = [u1, u2, ..., u...]. i ,…,u n ] T Where n represents the number of target companies or the number of target products; u i σ represents the expected rate of return of the target product of the i-th target enterprise. N =[σ N1 ,σ N2 ,…,σ Ni ,…,σ Nn ] T , where σ Ni This represents the resource allocation share for the i-th target product in the first current strategy N. For example, τ N-1 =[τ (N-1)1 ,τ (N-1)2 ,…,τ (N-1)i ,…,τ (N-1)n ] T , τ (N-1)i This represents the resource allocation share for the i-th target product in the first historical strategy N-1.

[0069] The first target policy can be determined based on the objective function value of the first current policy and the objective function value of the first historical policy. Optionally, determining the first target policy based on the objective function value of the first current policy and the objective function value of the first historical policy includes: if the objective function value of the first current policy is greater than the objective function value of the first historical policy, then the first current policy is determined as the first target policy.

[0070] For example, if the first current policy σ N The objective function value is X1, and the first historical strategy σ is obtained. N-1 The objective function value is X2. When X1 < X2, the first current policy is determined as the first objective policy.

[0071] The above technical solution uses the objective function value to iteratively update the new and old strategies, achieving accurate determination of the first target strategy in each iteration and cycle. When the objective function value of the first current strategy is determined to be less than that of the first historical strategy, it can be considered that the first current strategy is more in line with the resource allocation expectation than the first historical strategy in terms of the expected return of the current target product. Therefore, the strategy replacement method is adopted to improve the efficiency and accuracy of updating and iterating the optimization strategy of the investment portfolio.

[0072] Optionally, if the objective function value of the first current strategy is not greater than the objective function value of the first historical strategy, then the probability value of the first current strategy and the probability value of the first historical strategy are determined based on the objective function value of the first current strategy, the objective function value of the first historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle; and the first target strategy is determined based on the probability value of the first current strategy and the probability value of the first historical strategy.

[0073] When it is determined that the objective function value of the first current strategy is not greater than the objective function value of the first historical strategy, the probability values ​​of the first current strategy and the first historical strategy can be determined based on a preset probability determination function, according to the objective function value of the first current strategy, the objective function value of the first historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle.

[0074] For example, the probability determination function P σ The data is expressed in the following form:

[0075]

[0076] Among them, F σ (N) represents the objective function value of the first current policy; F σ(N-1) represents the objective function value of the first historical strategy; k represents the period value of the current cycle, for example, if the current cycle is the 30th cycle, then the value of k is 30; T represents the period value of the current iteration cycle, for example, if the current iteration cycle is the 50th iteration, then the value of T is 50. P σ This represents the probability value of the first current policy. 1-P σ This represents the probability value of the first historical strategy.

[0077] If the probability value of the first current strategy is greater than the probability value of the first historical strategy, then the first current strategy is determined as the first target strategy; if the probability value of the first current strategy is not greater than the probability value of the first historical strategy, then the first historical strategy is determined as the first target strategy.

[0078] The above technical solution achieves accurate determination of the first target strategy by determining that the objective function value of the first current strategy is not less than the objective function value of the first historical strategy, determining the probability value of the first current strategy and the probability value of the first historical strategy using a preset probability determination function, and selecting the first target strategy based on the probability value. This further improves the accuracy of determining the portfolio optimization strategy for the expected rate of return of the current target product.

[0079] Step a22: Based on the second current strategy, the expected rate of return of the target products of each target company, and the previous risk coefficient of each target company, determine the objective function value of the second current strategy based on the objective function value of the first historical strategy; determine the second target strategy based on the objective function value of the second current strategy and the objective function value of the second historical strategy.

[0080] For example, let's set the current loop cycle as the Nth iteration, and the preset objective optimization function is expressed as follows:

[0081]

[0082] Among them, F N (τ N ) represents the objective function value of the second current strategy in the Nth iteration; τ N For the second current strategy, u is the expected rate of return matrix of the target products of each target enterprise; η represents the momentum coupling parameter, which can be preset by relevant technical personnel according to actual needs, with a value range of [0,1]. Preferably, η can be set to 0.2. F N-1 (σ N-1 ) represents the objective function value of the first historical strategy in the N-1th cycle, i.e., the previous cycle; ∑ represents the risk coefficient between each target enterprise; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs.

[0083] Among them, u, σ N-1 and τ N All are n*1 matrices, for example, u = [u1, u2, ..., u...]. i ,…,u n ] T Where n represents the number of target companies or the number of target products; u i σ represents the expected rate of return of the target product of the i-th target enterprise. N-1 =[σ (N-1)1 ,σ (N-1)2 ,…,σ (N-1)i ,…,σ (N-1)n ] T , where σ (N-1)i This represents the resource allocation share for the i-th target product in the first historical strategy N-1. For example, τ N =[τ N1 ,τ N2 ,…,τ Ni ,…,τ Nn ] T , τ Ni This represents the resource allocation share for the i-th target product in the second current strategy N.

[0084] The first target strategy can be determined based on the objective function value of the second current strategy and the objective function value of the second historical strategy. Optionally, determining the second target strategy based on the objective function value of the second current strategy and the objective function value of the second historical strategy includes: if the objective function value of the second current strategy is greater than the objective function value of the second historical strategy, then the second current strategy is determined as the second target strategy.

[0085] If the objective function value of the second current strategy is not greater than the objective function value of the second historical strategy, then the probability value of the second current strategy and the probability value of the second historical strategy are determined based on the objective function value of the second current strategy, the objective function value of the second historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle; and the second target strategy is determined based on the probability value of the second current strategy and the probability value of the second historical strategy.

[0086] When determining that the objective function value of the second current strategy is not greater than the objective function value of the second historical strategy, the probability value of the second current strategy and the probability value of the second historical strategy can be determined based on a preset probability determination function, according to the objective function value of the second current strategy, the objective function value of the second historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle.

[0087] For example, the probability determination function P τ The data is expressed in the following form:

[0088]

[0089] Among them, F τ (N) represents the objective function value of the second current policy; F τ (N-1) represents the objective function value of the second historical strategy; k represents the period value of the current cycle, for example, if the current cycle is the 30th cycle, then the value of k is 30; T represents the period value of the current iteration cycle, for example, if the current iteration cycle is the 50th iteration, then the value of T is 50. P τ This represents the probability value of the second current policy. 1-P τ This represents the probability value of the second historical strategy.

[0090] If the probability value of the second current policy is greater than the probability value of the second historical policy, then the second current policy is determined as the second target policy; if the probability value of the second current policy is not greater than the probability value of the second historical policy, then the second historical policy is determined as the second target policy.

[0091] The above technical solution obtains the objective function values ​​of the first and second historical strategies. Based on the first current strategy, the company's expected rate of return, and the company's risk coefficient, and using the objective function value of the second historical strategy, it determines the objective function value of the first current strategy. Then, based on the objective function values ​​of the first current strategy and the first historical strategy, it determines the first target strategy. In determining the first target strategy, it comprehensively considers both the first and second historical strategies and iteratively updates the strategy based on the objective function values ​​corresponding to the current and historical strategies, thereby improving the accuracy of determining the first target strategy for each iteration and cycle. Similarly, the second target strategy is iteratively updated based on the objective function values ​​of the historical and current strategies, further improving the accuracy of determining the second target strategy for each iteration and cycle, and ultimately enhancing the accuracy of determining the optimization strategy for the target portfolio.

[0092] If the current iteration period meets the preset iteration termination condition and the current loop period meets the preset loop termination condition, then the optimization strategy for the target portfolio is determined according to the first objective strategy and the second objective strategy. Specifically, the loop termination condition can be that the current iteration period is the last iteration period and the current loop period is the last loop period. For example, if the set iteration period is 100 and the set loop period is 50, and the current iteration period is the 100th iteration and the current loop period is the 50th loop, then the loop termination condition is satisfied.

[0093] When a preset loop termination condition is met, either the first target strategy or the second target strategy can be determined as the optimized strategy for the target portfolio. To further improve the accuracy of determining the optimized strategy for the target portfolio, in an optional embodiment, determining the optimized strategy for the target portfolio based on the first target strategy and the second target strategy includes: determining the target similarity between the first target strategy and the second target strategy; if the target similarity is greater than a preset similarity threshold, then the first target strategy or the second target strategy is determined as the optimized strategy for the target portfolio.

[0094] For example, the target similarity between the strings of the first target strategy and the strings of the second target strategy can be determined based on a preset string matching algorithm, such as the edit distance algorithm or the maximum common subsequence algorithm. If the target similarity is greater than a preset similarity threshold, then both target strategies can be considered sufficiently accurate and can both be used as optimization strategies for the target portfolio. In this case, either the first target strategy or the second target strategy is determined as the optimization strategy for the target portfolio. The similarity threshold can be preset by relevant technical personnel according to actual needs; for example, the similarity threshold can be set to 90%.

[0095] For example, if both the first and second target strategies are [3000, 4000, 5000, 1000], then the target similarity is 100%, and [3000, 4000, 5000, 1000] is determined as the optimization strategy for the target portfolio.

[0096] The above technical solution improves the accuracy of determining the optimization strategy for the target portfolio by determining the target similarity between the first target strategy and the second target strategy, and by determining the first target strategy or the second target strategy as the optimization strategy for the target portfolio when the target similarity is greater than a preset similarity threshold.

[0097] If the target similarity is not greater than a preset similarity threshold, it can be considered that there is a certain deviation between the two strategies, and the global optimum has not been found; it may be a local optimum. In this case, the iteration count and loop count can be adjusted to continue the loop until the condition is met. For example, the iteration count and loop count can be increased until the target similarity between the first and second target strategies is greater than the preset similarity threshold.

[0098] If the current cycle is the first cycle, two initial policies are randomly generated, namely the first initial policy and the second initial policy. Let the first initial policy be σ. Ι The second initial strategy is τ Ι The objective function values ​​corresponding to the first and second initial strategies are determined as follows:

[0099]

[0100] Among them, F Ι (σ Ι F represents the objective function value of the first initial strategy; Ι (τ Ι ) represents the objective function value of the second initial strategy; u represents the expected rate of return matrix of the target products of each target company; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs; ∑ represents the risk coefficient between each target company.

[0101] This embodiment's technical solution generates a first current strategy based on a first historical strategy, and a second current strategy based on a second historical strategy. It also generates a first target strategy based on the first current strategy and the first historical strategy, considering the expected rate of return of the target product and the risk coefficients of each target company. Furthermore, it generates a second target strategy based on the second current strategy and the second historical strategy, considering the expected rate of return of the target product and the risk coefficients of each target company. This achieves the determination of the first and second target strategies for any iteration period and any number of iterations. By incorporating historical strategies from previous iteration periods during strategy determination and continuously optimizing the strategy in each iteration update, the optimal target strategy for the current iteration period and current number of iterations is obtained, thus improving the accuracy of determining the optimization strategy for the target investment portfolio.

[0102] Example 3

[0103] Figure 3 This is a flowchart illustrating a method for generating an optimization strategy for an investment portfolio according to Embodiment 3 of the present invention. This embodiment provides a preferred example based on the above embodiments.

[0104] like Figure 3 As shown, the method includes the following specific steps:

[0105] S1. Obtain the expected rate of return of the target product of at least one target company, set the number of iterations and the number of cycles in each iteration period, and set the initial combination strategy, which includes a first initial strategy and a second initial strategy.

[0106] In the momentum annealing algorithm, the number of iterations is equivalent to the set temperature, which is related to the convergence of the optimization problem. As the number of iterations increases, the temperature T gradually decreases, thus allowing the combinatorial convergence. The role of the neighborhood function is to partially change the combinatorial strategy based on a random number. For example, given the existing combinatorial strategy w is [3000, 4000, 5000, 1000], changing the value of a position in the vector by randomly generating a random number changes the current combinatorial w, resulting in the changed combinatorial strategy [3000, 5000, 4000, 1000].

[0107] Suppose that the first initial strategy is denoted as σ1 and the second initial strategy is denoted as τ1.

[0108] S2. Randomly generate perturbation quantities using a preset domain function to obtain two new combination strategies.

[0109] S3. Determine the objective function values ​​corresponding to the two new combination strategies.

[0110] The first initial policy σ1 is randomly generated based on a combination of perturbations to obtain the first current policy σ2. Similarly, the second initial policy τ1 is randomly generated based on a combination of perturbations to obtain the second current policy τ2. The objective function value of the first current policy σ2 is determined as follows:

[0111]

[0112] Since τ1 is the initial strategy, then Where F2(σ2) represents the objective function value of the first current strategy in the current second cycle; σ2 is the first current strategy in the second cycle; u is the expected rate of return matrix of the target products of each target enterprise; η represents the momentum coupling parameter, which can be preset by relevant technical personnel according to actual needs, and the value range is [0,1]. Preferably, η can be set to 0.2. F1(τ1) represents the objective function value of the second historical strategy in the first cycle, that is, in the previous cycle; ∑ represents the risk coefficient between each target enterprise; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs.

[0113] The method for determining the objective function value of the second current policy τ2 is similar. The method for determining the objective function value of the second current policy τ2 is as follows:

[0114]

[0115] Since σ1 is the initial policy, then Where F2(τ2) represents the objective function value of the second current strategy in the current second cycle; τ2 is the second current strategy in the second cycle; u is the expected rate of return matrix of the target products of each target enterprise; η represents the momentum coupling parameter, which can be preset by relevant technical personnel according to actual needs, and the value range is [0,1]. Preferably, η can be set to 0.2. F1(σ1) represents the objective function value of the first historical strategy in the first cycle, that is, in the previous cycle; ∑ represents the risk coefficient between each target enterprise; γ represents the risk coefficient factor, which can be preset by relevant technical personnel according to actual needs.

[0116] S4. Compare the objective function values ​​of the old and new strategies, and update and iterate the old and new strategies accordingly.

[0117] If the objective function value of the first current policy σ2 is greater than the objective function value of the first initial policy σ1, then the first current policy σ2 is adopted as the current optimal policy, and the first initial policy σ1 is discarded; if the objective function value of the first current policy σ2 is not greater than the objective function value of the first initial policy σ1, then the first current policy σ2 is adopted as the current optimal policy, and the first initial policy σ1 is discarded. The probability determines the current optimal strategy; if based on If the probability value of the first current policy σ2 is greater than that of the first initial policy σ1, then the first initial policy σ1 is discarded and the first current policy σ2 is adopted as the current optimal policy; otherwise, the first initial policy σ1 is still adopted as the current optimal policy.

[0118] If the objective function value of the second current policy τ2 is greater than the objective function value of the second initial policy τ1, then the second current policy τ2 is adopted as the current optimal policy, and the second initial policy τ1 is discarded; if the objective function value of the second current policy τ2 is not greater than the objective function value of the second initial policy τ1, then the second current policy τ2 is adopted as the optimal policy. The probability determines the current optimal strategy; if based on If the probability value of the second current policy τ2 is greater than that of the second initial policy τ1, then the second initial policy τ1 is discarded and the second current policy τ2 is adopted as the current optimal policy; otherwise, the second initial policy τ1 is still adopted as the current optimal policy.

[0119] S5. Repeat steps 2, 3 and 4 above for a preset number of iterations k times. The optimal strategy combination obtained is regarded as the optimal solution under the current iteration cycle.

[0120] S6. Repeat steps 2, 3, 4, and 5 above until the number of iterations reaches a set threshold, to obtain the optimal combination strategy σ. opti and τ opti .

[0121] S7. If two optimal combination strategies σ opti and τ opti If the two optimal combination strategies are the same, the algorithm is considered to have found the global optimum. If the two optimal combination strategies are different and significantly different, the iteration can be continued by adjusting the number of loops and iterations until the two optimal combination strategies σ are found. opti and τ opti If the strategies are the same or similar, the optimal combination strategy will be used as the optimization strategy for the target portfolio.

[0122] The information collected in this invention is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and public order and good morals are not violated. Corresponding operation portals are provided for users to choose to authorize or refuse.

[0123] Example 4

[0124] Figure 4 This is a schematic diagram of a portfolio optimization strategy generation device provided in Embodiment 4 of the present invention. The portfolio optimization strategy generation device provided in this embodiment of the present invention is applicable to generating optimization strategies for portfolios that meet the specific needs of specific individuals for corporate investment products. This portfolio optimization strategy generation device can be implemented in hardware and / or software, such as... Figure 4 As shown, the device includes: an expected rate of return determination module 401, a risk coefficient determination module 402, and an optimization strategy generation module 403. Among them,

[0125] Expected rate of return determination module 401 is used to determine the expected rate of return of a target product of at least one target enterprise.

[0126] The risk coefficient determination module 402 is used to determine the risk coefficient between the target companies based on the expected rate of return of the target products of each target company.

[0127] The optimization strategy generation module 403 is used to determine the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between each target enterprise; the optimization strategy of the target portfolio includes the resource allocation share of the target products of each target enterprise.

[0128] The technical solution of this invention determines the expected rate of return of the target product of at least one target enterprise, determines the risk coefficient between the target enterprises based on the expected rate of return of the target products of each target enterprise, and determines the optimization strategy of the target portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between the target enterprises. The technical solution of this invention realizes the automated determination of the optimization strategy of the target portfolio, improves the generation efficiency of the optimization strategy of the portfolio, and improves the accuracy of the generation of the optimization strategy of the portfolio by comprehensively considering the expected rate of return of the target products and the risk coefficient between enterprises in the process of determining the optimization strategy.

[0129] Optionally, the optimization strategy generation module 403 includes:

[0130] The historical combination strategy generation unit is used to obtain the historical combination strategy of the previous cycle under the current iteration cycle if the current iteration cycle is not the first iteration and the current loop cycle is not the first loop; the historical combination strategy includes a first historical strategy and a second historical strategy.

[0131] The current strategy generation unit is configured to generate a first current strategy based on the first historical strategy, and to generate a second current strategy based on the second historical strategy;

[0132] The target strategy generation unit is configured to generate a first target strategy based on the first current strategy and the first historical strategy, and based on the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past; and to generate a second target strategy based on the second current strategy and the second historical strategy, and based on the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past.

[0133] The optimization strategy generation unit is used to determine the optimization strategy of the target portfolio based on the first target strategy and the second target strategy if the current iteration period meets the preset iteration end condition and the current cycle period meets the preset cycle end condition.

[0134] Optionally, the target policy generation unit includes:

[0135] The historical function value acquisition subunit is used to acquire the objective function values ​​of the first historical strategy and the second historical strategy.

[0136] The first objective function value determination subunit is used to determine the objective function value of the first current strategy based on the objective function value of the second historical strategy, according to the first current strategy, the expected rate of return of the target products of each target enterprise, and the risk coefficient of each target enterprise in the past.

[0137] The first target strategy determination subunit is configured to determine a first target strategy based on the objective function value of the first current strategy and the objective function value of the first historical strategy; and,

[0138] The second objective function value determination subunit is used to determine the objective function value of the second current strategy based on the objective function value of the first historical strategy, according to the second current strategy, the expected rate of return of the target products of each target enterprise, and the risk coefficient of each target enterprise in the past.

[0139] The second target strategy determination subunit is used to determine the second target strategy based on the target function value of the second current strategy and the target function value of the second historical strategy.

[0140] Optionally, the first objective strategy determines the sub-unit, specifically used for:

[0141] If the objective function value of the first current strategy is greater than the objective function value of the first historical strategy, then the first current strategy is determined as the first objective strategy.

[0142] Optionally, the first target strategy determining the sub-unit is also used for:

[0143] If the objective function value of the first current strategy is not greater than the objective function value of the first historical strategy, then the probability value of the first current strategy and the probability value of the first historical strategy are determined based on the objective function value of the first current strategy, the objective function value of the first historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle.

[0144] The first target strategy is determined based on the probability value of the first current strategy and the probability value of the first historical strategy.

[0145] Optionally, the optimization strategy generation unit is specifically used for:

[0146] Determine the target similarity between the first target strategy and the second target strategy;

[0147] If the target similarity is greater than a preset similarity threshold, then the first target strategy or the second target strategy is determined as the optimization strategy for the target portfolio.

[0148] The portfolio optimization strategy generation device provided in this embodiment of the invention can execute the portfolio optimization strategy generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0149] Example 5

[0150] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0151] like Figure 5As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0152] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0153] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as portfolio optimization strategy generation methods.

[0154] In some embodiments, the portfolio optimization strategy generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the portfolio optimization strategy generation method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the portfolio optimization strategy generation method by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0160] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0161] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating an optimization strategy for a portfolio, characterized in that, include: Determine the expected rate of return for the target product of at least one target company; Based on the expected rate of return of the target products of each target company, determine the risk coefficient among the target companies; Based on the expected rate of return of the target products of each target company, and based on the risk coefficients among the target companies, an optimization strategy for the target portfolio is determined. The optimization strategy for the target portfolio includes the allocation of resources to the target products of each of the target companies.

2. The method according to claim 1, characterized in that, The step of determining the optimization strategy for the target investment portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficients among the target enterprises includes: If the current iteration period is not the first iteration and the current cycle period is not the first cycle, then obtain the historical combination strategy of the previous cycle period under the current iteration period; the historical combination strategy includes the first historical strategy and the second historical strategy. A first current strategy is generated based on the first historical strategy, and a second current strategy is generated based on the second historical strategy; Based on the first current strategy and the first historical strategy, a first target strategy is generated based on the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past; and based on the second current strategy and the second historical strategy, a second target strategy is generated based on the expected rate of return of the target products of each target enterprise and the risk coefficient of each target enterprise in the past. If the current iteration period meets the preset iteration end condition and the current cycle period meets the preset cycle end condition, then the optimization strategy of the target portfolio is determined according to the first target strategy and the second target strategy.

3. The method according to claim 2, characterized in that, The step of generating a first target strategy based on the first current strategy and the first historical strategy, and based on the expected rate of return of the target products of each target enterprise and the previous risk coefficient of each target enterprise, and generating a second target strategy based on the second current strategy and the second historical strategy, and based on the expected rate of return of the target products of each target enterprise and the previous risk coefficient of each target enterprise, includes: Obtain the objective function values ​​of the first historical strategy and the second historical strategy; Based on the first current strategy, the expected rate of return of the target products of each target company, and the previous risk coefficient of each target company, the objective function value of the first current strategy is determined based on the objective function value of the second historical strategy. Based on the objective function value of the first current strategy and the objective function value of the first historical strategy, a first target strategy is determined; and, Based on the second current strategy, the expected rate of return of the target products of each target company, and the previous risk coefficient of each target company, the objective function value of the second current strategy is determined based on the objective function value of the first historical strategy. The second target strategy is determined based on the objective function value of the second current strategy and the objective function value of the second historical strategy.

4. The method according to claim 3, characterized in that, The step of determining the first target strategy based on the objective function value of the first current strategy and the objective function value of the first historical strategy includes: If the objective function value of the first current strategy is greater than the objective function value of the first historical strategy, then the first current strategy is determined as the first objective strategy.

5. The method according to claim 4, characterized in that, The method further includes: If the objective function value of the first current strategy is not greater than the objective function value of the first historical strategy, then the probability value of the first current strategy and the probability value of the first historical strategy are determined based on the objective function value of the first current strategy, the objective function value of the first historical strategy, the period value of the current iteration cycle, and the period value of the current loop cycle. The first target strategy is determined based on the probability value of the first current strategy and the probability value of the first historical strategy.

6. The method according to claim 2, characterized in that, The step of determining the optimization strategy for the target portfolio based on the first target strategy and the second target strategy includes: Determine the target similarity between the first target strategy and the second target strategy; If the target similarity is greater than a preset similarity threshold, then the first target strategy or the second target strategy is determined as the optimization strategy for the target portfolio.

7. An apparatus for generating portfolio optimization strategies, characterized in that, include: The expected rate of return determination module is used to determine the expected rate of return of a target product of at least one target enterprise. The risk coefficient determination module is used to determine the risk coefficient between the target companies based on the expected rate of return of the target products of each target company. The optimization strategy generation module is used to determine the optimization strategy of the target investment portfolio based on the expected rate of return of the target products of each target enterprise and the risk coefficient between each target enterprise. The optimization strategy for the target portfolio includes the allocation of resources to the target products of each of the target companies.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the portfolio optimization strategy generation method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the portfolio optimization strategy generation method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the portfolio optimization strategy generation method according to any one of claims 1-6.

Images