Product net value prediction method, device, equipment and medium
By identifying the score values and other influencing factors of the product manager, and using pre-trained models to predict products such as funds, the problem of inaccurate prediction in the existing technology is solved, and fast and accurate net value prediction is achieved.
Patent Information
- Application Number
- CN202411234878.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-06
AI Technical Summary
It is difficult for the existing technology to quickly and accurately predict the net value of funds and other products, which affects the accuracy of customer decision-making references.
By identifying product manager scores and other influencing factors, a pre-trained model is used to predict net value, including parameter evaluation of product timing, risk resistance and return ability.
It realizes rapid and accurate prediction of product net value and improves the accuracy and reliability of decision-making references.
Smart Images

Figure CN119090642A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a product net value prediction method, device, equipment and medium. Background Art
[0002] With the rapid development of social economy, in recent years, funds and other products have developed rapidly in the financial market and become an important means of asset allocation for customers. Among them, it is very important and necessary to predict the future net value of the product in advance to provide decision-making reference for customers.
[0003] However, how to quickly and accurately predict the net value of a product is a technical problem that urgently needs to be solved. Summary of the invention
[0004] The present application provides a product net value prediction method, device, equipment and medium for quickly and accurately predicting the net value of a product.
[0005] In a first aspect, the present application provides a method for predicting a product net value, the method comprising:
[0006] For any product to be predicted for net worth, identify the product manager of the product, obtain the parameter values of each setting parameter that affects the product manager's score, input each parameter value into a pre-trained product manager score determination model, and determine the product manager's score according to the output result of the product manager score determination model; and obtain information on other setting factors that affect the product's net worth other than the product manager;
[0007] The product manager's score and the information of the other set factors are input into the trained product net value prediction model, and the net value prediction value of the product is obtained according to the output result of the product net value prediction model.
[0008] In a possible implementation manner, obtaining the parameter values of the setting parameters that affect the score value of the product manager includes:
[0009] If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager;
[0010] For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate;
[0011] For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score;
[0012] Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
[0013] In a possible implementation manner, determining the first product performance score based on the second net worth growth rate and the first net worth growth rate includes:
[0014] If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score;
[0015] If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
[0016] In a possible implementation, determining the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate includes:
[0017] If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score;
[0018] If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
[0019] In a possible implementation, determining the second sub-selected product timing capability parameter value based on at least one of the first product performance score and the second product performance score includes:
[0020] The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
[0021] In a possible implementation manner, obtaining the parameter values of the setting parameters that affect the score value of the product manager includes:
[0022] If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager;
[0023] Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
[0024] In a possible implementation, determining the parameter value of the risk resistance parameter based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value includes:
[0025] Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility;
[0026] The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
[0027] In a possible implementation manner, obtaining the parameter values of the setting parameters that affect the score value of the product manager includes:
[0028] If the set parameters include profitability parameters, the yields of products of the various product strategies corresponding to the product manager are obtained;
[0029] The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
[0030] In a possible implementation, the setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, academic qualifications, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
[0031] In a second aspect, the present application provides a product net value prediction device, the device comprising:
[0032] An acquisition module is used to identify the product manager of any product for which net value prediction is to be performed, obtain parameter values of various setting parameters that affect the product manager's score value, input each of the parameter values into a pre-trained product manager score value determination model, and determine the product manager's score value according to the output result of the product manager score value determination model; and obtain information on various other setting factors that affect the product's net value in addition to the product manager;
[0033] The prediction module is used to input the product manager's score value and the information of the other set factors into the trained product net value prediction model, and obtain the net value prediction value of the product according to the output result of the product net value prediction model.
[0034] In a possible implementation manner, the acquisition module is specifically configured to:
[0035] If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager;
[0036] For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate;
[0037] For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score;
[0038] Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
[0039] In a possible implementation manner, the acquisition module is specifically configured to:
[0040] If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score;
[0041] If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
[0042] In a possible implementation manner, the acquisition module is specifically configured to:
[0043] If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score;
[0044] If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
[0045] In a possible implementation manner, the acquisition module is specifically configured to:
[0046] The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
[0047] In a possible implementation manner, the acquisition module is specifically configured to:
[0048] If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager;
[0049] Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
[0050] In a possible implementation manner, the acquisition module is specifically configured to:
[0051] Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility;
[0052] The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
[0053] In a possible implementation manner, the acquisition module is specifically configured to:
[0054] If the set parameters include profitability parameters, the yields of products of the various product strategies corresponding to the product manager are obtained;
[0055] The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
[0056] In a possible implementation, the setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, academic qualifications, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
[0057] In a third aspect, an embodiment of the present application further provides an electronic device, including:
[0058] A memory for storing program instructions;
[0059] The processor is used to call the program instructions stored in the memory, and execute the steps included in any one of the methods in the first aspect according to the obtained program instructions.
[0060] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer performs the steps of the method as described in any one of the first aspects.
[0061] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the steps of the method described in any one of the first aspects.
[0062] In the embodiment of the present application, for any product to be predicted for net value, the product manager of the product can be identified, the parameter values of each setting parameter affecting the product manager's score value can be obtained, and each parameter value can be input into a pre-trained product manager score value determination model, and the product manager's score value can be determined according to the output result of the product manager score value determination model; and the information of each other setting factor affecting the product's net value other than the product manager can be obtained; the product manager's score value and the information of each other setting factor can be input into the trained product net value prediction model, and the product's net value prediction value can be obtained according to the output result of the product net value prediction model. Since the present application can obtain the product manager's score value based on the parameter values of each setting parameter affecting the product manager's score value as quickly, intelligently and accurately as possible, and obtain the product's net value prediction value based on the product manager's score value and the information of each other setting factor affecting the product's net value other than the product manager as quickly, intelligently, accurately and comprehensively as possible, the accuracy of the product's net value prediction value can be improved, and the purpose of predicting the product's net value as quickly and accurately as possible can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] In order to more clearly illustrate the implementation methods in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technology descriptions. Obviously, the drawings described below are some embodiments of the present application, and a person skilled in the art can also obtain other drawings based on these drawings.
[0064] Figure 1 A schematic diagram of a first product net value prediction process provided by some embodiments is shown;
[0065] Figure 2 A schematic diagram of a second product net value prediction process provided by some embodiments is shown;
[0066] Figure 3 A schematic diagram of a third product net value prediction process provided by some embodiments is shown;
[0067] Figure 4 A schematic diagram of a fourth product net value prediction process provided by some embodiments is shown;
[0068] Figure 5 A schematic diagram of a fifth product net value prediction process provided by some embodiments is shown;
[0069] Figure 6 A schematic diagram of a sixth product net value prediction process provided by some embodiments is shown;
[0070] Figure 7 A schematic diagram of a product net value prediction device provided by some embodiments is shown;
[0071] Figure 8 A schematic diagram of the structure of an electronic device provided by some embodiments is shown. DETAILED DESCRIPTION
[0072] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.
[0073] The terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. "Multiple" in the present application can mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.
[0074] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.
[0075] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.
[0076] Before introducing the product net worth prediction method provided in the embodiment of the present application, in order to facilitate understanding, the technical background of the embodiment of the present application is first introduced.
[0077] In the related technologies, taking funds as an example, it is very important and necessary to predict the future net value of funds and other products in advance to provide decision-making references for customers. However, there is currently no good solution for how to quickly and accurately predict the net value of products. Therefore, a technical solution that can quickly and accurately predict the net value of products is urgently needed.
[0078] In view of this, in order to quickly and accurately predict the net value of a product, the embodiments of the present application propose a method, device, equipment and medium for predicting the net value of a product. Some preferred embodiments of the present application are described below in conjunction with the accompanying drawings.
[0079] Embodiment 1:
[0080] Figure 1 A schematic diagram of a first product net value prediction process provided by some embodiments is shown, such as Figure 1 As shown, the process includes the following steps:
[0081] S101: For any product to be predicted for net worth, identify the product manager of the product, obtain parameter values of various setting parameters that affect the product manager's score, input each of the parameter values into a pre-trained product manager score determination model, and determine the product manager's score according to the output result of the product manager score determination model; and obtain information on other setting factors that affect the product's net worth except the product manager.
[0082] The product net value prediction method provided in the embodiment of the present application is applied to an electronic device, which may be, for example, a personal computer (PC), a mobile terminal, a server, etc., and the present application does not specifically limit this. In addition, the present application does not specifically limit the specific type of the product for which the net value prediction is performed, for example, the product may be a fund, such as a stock fund, etc.
[0083] In a possible implementation, considering that the decisions of product managers (such as fund managers) usually affect the rise and fall of product net value, in order to improve the accuracy of product net value prediction, for any product to be predicted for product net value, the product manager in charge of the product can be identified first, and then the parameter values of the preset parameters that affect the product manager's score can be obtained, and the ability of the product manager is analyzed and evaluated through these parameter values, and then the net value of the product is accurately predicted based on the analysis and evaluation results of the product manager's ability. Specifically, the preset parameters that affect the product manager's score can include the following five parameters:
[0084] (1) Product manager attribute parameters.
[0085] In a possible implementation, the product manager attribute parameters may include: the product manager's age, graduation school, major studied, academic qualifications, working time and even gender, etc., which can be flexibly set according to needs, and this application does not make specific limitations on this.
[0086] (2) Attribute parameters of the products under the management of the product manager (for ease of description, referred to as managed product attribute parameters).
[0087] In a possible implementation, the jurisdiction product attribute parameters may include: net value growth rate, net value volatility and other parameters of the products under the jurisdiction of the product manager. Among them, when the number of products under the jurisdiction of the product manager is multiple, the net value growth rate in the jurisdiction product attribute parameters may be the average value, median value, minimum value or maximum value of the net value growth rates of the multiple products under the jurisdiction of the product manager, etc., and the present application does not make specific restrictions on this. Similarly, when the number of products under the jurisdiction of the product manager is multiple, the net value volatility in the jurisdiction product attribute parameters may be the average value, median value, minimum value or maximum value of the net value volatility of the multiple products under the jurisdiction of the product manager, etc., and the present application does not make specific restrictions on this. Among them, the existing technology can be used to determine the net value growth rate, net value volatility, etc. of any product, which will not be repeated here.
[0088] (3) Product manager’s profitability parameters.
[0089] In a possible implementation, when determining the parameter value of the product manager's profitability (also referred to as money-making ability) parameter, the yields of products of various product strategies (also referred to as investment strategies) such as fixed investment or non-fixed investment that the product manager manages (corresponds to) within a set time period such as the past year, the past three years, the past six months, and this year can be obtained. For example, for any fund product, the average yield of investment (non-fixed investment) on any day in the past year to date, and the average yield of fixed investment in the past year according to a set time period such as every day, every three days, every week, or every half a month to date can be obtained. Afterwards, for any product strategy (investment strategy), the average yield of all products of the product strategy can be used as the yield of the product strategy, and then the weighted sum of the yields of the products of the product manager's various product strategies can be determined as the parameter value of the product manager's profitability parameter.
[0090] For ease of description, the process of determining the parameter value of the product manager's profitability (profitability parameter) is explained in the form of a formula. The parameter value of profitability can be calculated using the following formula: Earn = ε 1 Tou+∈ 1DTou, where Earn represents the profitability parameter value of the product manager, Tou represents the rate of return of the product using the above non-fixed investment product strategy (investment strategy), DTou represents the rate of return of the product using the above fixed investment product strategy (investment strategy), and ε 1 is the weight factor of the yield of the product strategy based on the above non-fixed investment method, ∈ 1 is the weight factor of the rate of return of the product with the above fixed investment strategy. 1 and ∈ 1 The specific value of can be calculated based on the Delphi method, the analytic hierarchy process (AHP), etc., which is not specifically limited in this application and will not be repeated here. In a possible implementation, ε 1 and ∈ 1 The sum of can be set to 1 or other values.
[0091] (4) Parameters of product manager’s ability to select products and time the product.
[0092] Taking the product as a stock fund as an example, when determining the parameter value of the product manager's product selection and timing ability (also known as stock selection ability and timing ability), the target fund (target product) whose stocks (sub-products) included in the fund (product) have been changed by the product manager can be identified first. Among them, for any product, the product corresponds to information on whether the sub-products included in the product have been changed, and which product manager has changed the sub-products included in the product. Based on this information, the target product whose sub-products have been changed by a certain product manager can be identified (selected) from various products.
[0093] For each sub-product (stock) currently included in the target product (target fund), that is, for each sub-product after the target product is changed, the proportion of the sub-product in the target product (ω i ) and the net value growth rate of the sub-product (R i ), wherein the proportion of sub-products (stocks) in the product and the net value growth rate of sub-products can be determined by existing technologies, which will not be described in detail here. Afterwards, the sum of the product of the proportion of each sub-product (a total of n sub-products) and the net value growth rate of the sub-product can be determined. The sum of the product of the proportion of each sub-product and the net value growth rate of the sub-product can be calculated. Determine the timing ability parameter value (Cho) for the first sub-selected product.
[0094] In a possible implementation, for the target product, the first net value growth rate of the target product before the sub-product is changed (for ease of description, represented by old), the second net value growth rate after the sub-product is changed (for ease of description, represented by new), and the third net value growth rate of the product market as a whole (i.e., the market) can also be determined within a set time. Among them, the process of determining the first net value growth rate, the second net value growth rate, and the third net value growth rate of the product market as a whole (the market) can adopt existing technologies, which will not be repeated here.
[0095] In one possible implementation, in order to measure the product manager's ability to select products and timing, the first product performance score can be determined based on the values of the second net worth growth rate (new) and the first net worth growth rate (old), and the second product performance score can be determined based on the values of the second net worth growth rate (new) and the third net worth growth rate.
[0096] Specifically, when determining the performance score of the first product, if the second net worth growth rate (new) and the first net worth growth rate (old) are both positive or both negative, then the ratio of the second net worth growth rate to the first net worth growth rate is calculated. In addition, if the second net worth growth rate (old) is negative and the first net worth growth rate (old) is positive, the ratio of the second net worth growth rate to the first net worth growth rate can be determined as the first product performance score. Determined as the first product performance score.
[0097] In one possible implementation, if the second net worth growth rate (new) is a positive number and the first net worth growth rate (old) is a negative number, considering that the growth rate of the product after the sub-product is changed by the product manager is better than the growth rate of the product before the sub-product is changed, the product manager's ability to select products and time is still relatively strong, but at this time the ratio of the second net worth growth rate to the first net worth growth rate is negative. At this time, the ratio of the second net worth growth rate to the first net worth growth rate cannot accurately reflect the product manager's ability to select products and time. In order to quickly and accurately reflect the product manager's ability to select products and time, the second net worth growth rate (new), which is a positive number, can be directly determined as the first product performance score.
[0098] Based on the same concept as determining the first recent performance score, when determining the second product performance score, if the second net worth growth rate (new) and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate (new) is negative and the third net worth growth rate is positive, then the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score. If the second net worth growth rate (new) is positive and the third net worth growth rate is negative, in order to quickly and accurately reflect the product manager's ability to select products and time, the second net worth growth rate (new) can be directly determined as the second product performance score.
[0099] In a possible implementation, after determining the performance score of the first product and the performance score of the second product, the maximum value, minimum value or average value of the first product performance score and the second product performance score can be directly determined as the second sub-selection product timing ability parameter value (Gtime). In a possible implementation, in order to accurately determine the second sub-selection product timing ability parameter value (Gtime), the product between the first product performance score, the second product performance score and the set adjustment factor can be determined as the second sub-selection product timing ability parameter value (Gtime). For ease of description, the process of determining the second sub-selection product timing ability parameter value (Gtime) is explained in formula form below.
[0100] Exemplarily, it is assumed that the determination process of the timing capability parameter value (Gtime) of the second sub-selected product is determined by the following formula: in, represents the performance score of the first product, μ represents the performance score of the second product, and γ represents the set adjustment factor.
[0101] Among them, the adjustment factor γ is mainly used to adjust whether the final calculated Gtime is a positive number or a negative number. For example, when the second net asset growth rate is negative, the first net asset growth rate is positive, and the third net asset growth rate is positive, the calculated performance score of the first product is is a negative number and the second product performance score μ is a negative number. In this case, it can be considered that the product manager has brought negative effects on the adjustment of the sub-products in the product, and it can be considered that the product manager's ability to select products and time is weak. If the two negative numbers, the first product performance score and the second product performance score, are directly multiplied, the product of the first product performance score and the second product performance score is a positive number, which cannot accurately reflect the product manager's ability to select products and time. In this case, in order to accurately reflect the product manager's ability to select products and time, the value of the adjustment factor γ can be configured to a set negative value such as -1, so that the product of the first product performance score, the second product performance score and the set adjustment factor is a negative value.
[0102] In a possible implementation, in addition to the above situation, the value of the adjustment factor γ can be set to a positive value such as 1, so that the product of the first product performance score, the second product performance score and the set adjustment factor can accurately reflect the product manager's ability to select products and time to a certain extent.
[0103] In one possible implementation, after determining the first sub-product selection timing ability parameter value (Cho) and the second sub-product selection timing ability parameter value (Gtime), the parameter value (Chose) of the product manager's product selection timing ability parameter can be determined based on the weighted sum of the first sub-product selection timing ability parameter value (Cho) and the second sub-product selection timing ability parameter value (Gtime).
[0104] For ease of description, the process of determining the parameter value of the product manager's product timing ability (product timing ability parameter) is explained in the form of a formula. The parameter value of the product timing ability parameter can be calculated using the following formula: Chose = ε 2 Cho+∈ 2 Gtime, where Chose represents the product manager's product selection and timing ability parameter value, Cho represents the first sub-product selection and timing ability parameter value, Gtime represents the second sub-product selection and timing ability parameter value, ε 2 is the weight factor of the first sub-selected product timing capability parameter value, ∈ 2 The weight factor of the second sub-selected product timing capability parameter value. ε 2 and ∈ 2 The specific value of can be calculated based on the Delphi method, the hierarchical analysis method, etc., which is not specifically limited in this application and will not be repeated here. In a possible implementation, ε 2 and ∈ 2 The sum of can be set to 1 or other values.
[0105] (5) Product manager’s risk resistance parameters.
[0106] In a possible implementation, when determining the parameter value of the product manager's risk resistance parameter, the first net value volatility of the product market as a whole (the market) within a set time, the second net value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager can be obtained. Among them, when the product manager corresponds to multiple products, the maximum value, minimum value, median value or average value of the net value volatility of the multiple products corresponding to the product manager can be determined as the second net value volatility of the product corresponding to the product manager. Existing technology can be used to determine the first net value volatility of the market, the net value volatility of any product, and the maximum drawdown index value, which will not be repeated here.
[0107] After obtaining the above-mentioned first net asset volatility, second net asset volatility and maximum drawdown index value, the parameter value of the product manager's risk resistance parameter can be determined based on the first net asset volatility, second net asset volatility and maximum drawdown index value. Exemplarily, the weighted sum of the first net asset volatility, the second net asset volatility and the maximum drawdown index value can be determined as the parameter value of the product manager's risk resistance parameter.
[0108] For ease of description, the process of determining the parameter value of the product manager's risk resistance (risk resistance parameter) is explained in the form of a formula below. The parameter value of the risk resistance parameter can be calculated using the following formula: Kang = φDT + ωDB + θMH, where Kang represents the parameter value of the risk resistance parameter, DT represents the first net value volatility, DB represents the second net value volatility, MH represents the maximum drawdown index value, φ is the weight factor of the first net value volatility, ω is the weight factor of the second net value volatility, θ is the weight factor of the maximum drawdown index value, and the specific values of φ, ω and θ can be calculated based on the Delphi method, hierarchical analysis method, etc. This application does not make specific limitations on this and will not be repeated here. In one possible implementation, the sum of φ, ω and θ can be a set value such as 1.
[0109] In one possible implementation, when determining the parameter value of the product manager's risk resistance parameter based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the third product performance score can also be determined based on the values of the second net asset value volatility and the first net asset value volatility. Thereafter, the weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the product manager's risk resistance parameter.
[0110] When determining the performance score of the third product based on the values of the second net asset volatility and the first net asset volatility, if the second net asset volatility (DB) and the first net asset volatility (DT) of the market are both positive or negative, then the ratio of the second net asset volatility to the first net asset volatility is used as the performance score of the third product. In addition, if the second net asset volatility (DB) is negative and the first net asset volatility (DT) of the market is positive, the ratio of the second net asset volatility to the first net asset volatility can be used to determine the performance score of the third product. Determined as the third product performance score.
[0111] In one possible implementation, when the second net value volatility (DB) is a positive number and the first net value volatility (DT) of the market is a negative number, the product manager's risk resistance is still relatively strong, but the ratio of the second net value volatility to the first net value volatility is negative. At this time, the ratio of the second net value volatility to the first net value volatility cannot accurately reflect the product manager's risk resistance. In order to quickly and accurately reflect the product manager's risk resistance, the positive second net value volatility (DB) can be directly determined as the third product performance score.
[0112] For ease of understanding, if the third product performance score is The third product performance score The weighted sum of the second net asset volatility DB and the maximum drawdown index value MH is used to determine the parameter value of the product manager's risk resistance parameter. The formula can be used: It means that I will not elaborate on it here.
[0113] In a possible implementation, after obtaining the parameter values of each setting parameter that affects the product manager's score, the parameter values of each setting parameter obtained can be input into a pre-trained product manager score determination model. The product manager score determination model can analyze each parameter value and determine the score corresponding to each parameter value. The electronic device can determine the product manager's score based on the output result of the product manager score determination model. Exemplarily, the product manager score determination model can be a model such as a multilayer perceptron (MLP). The product manager score determination model can use a hyperbolic tangent activation function (tanh) to output an initial score in the interval [-1,1]. The electronic device can multiply the initial score in the interval [-1,1] by 100 to obtain the final score of the product manager. The training process of the product manager score determination model will be introduced later and will not be repeated here.
[0114] In a possible implementation, in order to improve the accuracy of the net value prediction of the product, in addition to obtaining the rating of the product manager, information of other setting factors that affect the net value of the product other than the product manager can also be obtained. Exemplarily, the information of other setting factors may include the following information:
[0115] (1) Product (such as fund) time series characteristic information.
[0116] The product time series feature information may include at least one of the product's net value, product price fluctuation, cumulative net value, fixed investment (including ordinary fixed investment, smart fixed investment, etc.) returns in historical time periods such as the past 7 days, the past month, and the past 3 months.
[0117] (2) Basic characteristic information of the product.
[0118] The basic characteristic information of the product may include: the year the product (fund) was established, the categories and proportions of the fund's heavily weighted stocks in the product, the product's (fund's) ranking among peers, industry benchmarks, product size (such as fund size), custodian company, investment philosophy, investment strategy, holder structure, number of dividends, etc., among at least one of the following characteristic information.
[0119] (3) Information on market factors.
[0120] Information on market factors may include information on at least one of product company situation factors, industry factors, macroeconomic factors, policy factors, international factors, market sentiment factors and investor sentiment factors.
[0121] Among them, product company situation factors may include: the product company's financial situation, performance, growth potential, management team capabilities and other factors. Industry factors may include: the overall performance of the industry in which the product is located, industry prospects and industry competition pattern and other factors. Macroeconomic factors may include: gross domestic product (GDP) and other macroeconomic indicators, inflation rate, interest rate level, employment situation, economic growth index, inflation expectations, monetary policy and other factors. International factors may include: international politics, international economy, geopolitics, international events, the performance and behavior of multinational companies, foreign exchange markets and other factors. Among them, existing technologies can be used to obtain information on the above-mentioned other set factors, which will not be repeated here.
[0122] S102: Input the product manager's score value and the information of the other set dimensions into the trained product net worth prediction model, and obtain the net worth prediction value of the product according to the output result of the product net worth prediction model.
[0123] In one possible implementation, after obtaining the product manager's score and information of other set dimensions, the product manager's score and information of the above-mentioned other set factors can be input into a trained product net worth prediction model. The product net worth prediction model analyzes the product manager's score and information of the above-mentioned other set factors, and outputs a net worth prediction value for the product. Based on this, the electronic device can obtain a net worth prediction value for the product.
[0124] In the embodiment of the present application, for any product to be predicted for net value, the product manager of the product can be identified, the parameter values of each setting parameter affecting the product manager's score value can be obtained, and each parameter value can be input into a pre-trained product manager score value determination model, and the product manager's score value can be determined according to the output result of the product manager score value determination model; and the information of each other setting factor affecting the product's net value other than the product manager can be obtained; the product manager's score value and the information of each other setting factor can be input into the trained product net value prediction model, and the product's net value prediction value can be obtained according to the output result of the product net value prediction model. Since the present application can obtain the product manager's score value based on the parameter values of each setting parameter affecting the product manager's score value as quickly, intelligently and accurately as possible, and obtain the product's net value prediction value based on the product manager's score value and the information of each other setting factor affecting the product's net value other than the product manager as quickly, intelligently, accurately and comprehensively as possible, the accuracy of the product's net value prediction value can be improved, and the purpose of predicting the product's net value as quickly and accurately as possible can be achieved.
[0125] For ease of understanding, the product net value prediction process provided by this application is explained below through a specific embodiment. Figure 2 , Figure 2 A schematic diagram of a second product net value prediction process provided by some embodiments is shown, and the process includes the following steps:
[0126] S201: For any product to be predicted for net value, identify the product manager of the product, obtain the parameter values of each setting parameter that affects the product manager's score, and obtain information on other setting factors that affect the product's net value other than the product manager. Among them, when the setting parameters that affect the product manager's score include the risk resistance parameter, the first net value volatility of the market within the set time, the second net value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager can be obtained, and the parameter value of the risk resistance parameter is determined based on the first net value volatility, the second net value volatility and the maximum drawdown index value.
[0127] S202: Inputting parameter values of set parameters that affect the product manager's score into a pre-trained product manager's score determination model, and determining the product manager's score according to an output result of the product manager's score determination model.
[0128] S203: Input the product manager's score value and information of other set factors into the trained product net value prediction model, and obtain the product's net value prediction value based on the output result of the product net value prediction model.
[0129] For ease of understanding, the product net value prediction process provided by this application is explained below through a specific embodiment. Figure 3 , Figure 3 A schematic diagram of a third product net value prediction process provided by some embodiments is shown, and the process includes the following steps:
[0130] S301: For any product to be predicted for net worth, identify the product manager of the product, obtain parameter values of various setting parameters that affect the product manager's score, and obtain information on other setting factors that affect the product's net worth except the product manager. Among them, the setting parameters that affect the product manager's score value include a product selection timing ability parameter, which identifies the target product whose sub-products are changed by the product manager; for each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net asset value growth rate of the sub-product; determine the first sub-product timing ability parameter value based on the product of the proportion of each sub-product and the sub-product net asset value growth rate; for the target product, determine the first net asset value growth rate of the target product before the sub-product is changed, the second net asset value growth rate after the sub-product is changed, and the third net asset value growth rate of the market within the set time; determine the first product performance score based on the second net asset value growth rate and the values of the first net asset value growth rate, and determine the second product performance score based on the second net asset value growth rate and the values of the third net asset value growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score; and determine the weighted sum of the first sub-product timing ability parameter value and the second sub-product timing ability parameter value as the parameter value of the product selection timing ability parameter.
[0131] S302: Inputting parameter values of set parameters that affect the product manager's score into a pre-trained product manager's score determination model, and determining the product manager's score according to an output result of the product manager's score determination model.
[0132] S303: Input the product manager's score value and information of other set factors into the trained product net value prediction model, and obtain the product's net value prediction value based on the output result of the product net value prediction model.
[0133] For ease of understanding, the product net value prediction process provided by this application is explained below through a specific embodiment. Figure 4 , Figure 4 A schematic diagram of a fourth product net value prediction process provided by some embodiments is shown, and the process includes the following steps:
[0134] S401: For any product to be predicted for net value, identify the product manager of the product, obtain the parameter values of each setting parameter that affects the product manager's score, and obtain information on other setting factors that affect the product's net value other than the product manager. When the setting parameters that affect the product manager's score include a profitability parameter, obtain the yields of the products of the various product strategies corresponding to the product manager; determine the parameter value of the profitability parameter of the product manager based on the weighted sum of the yields of the products of the various product strategies.
[0135] S402: Inputting parameter values of set parameters that affect the product manager's score into a pre-trained product manager's score determination model, and determining the product manager's score according to an output result of the product manager's score determination model.
[0136] S403: Input the product manager's score value and information of other set factors into the trained product net value prediction model, and obtain the product's net value prediction value based on the output result of the product net value prediction model.
[0137] For ease of understanding, the product net value prediction process provided by this application is explained below through a specific embodiment. Figure 5 , Figure 5 A schematic diagram of a fifth product net value prediction process provided by some embodiments is shown, and the process includes the following steps:
[0138] S501: For any product to be predicted for net value, identify the product manager of the product, obtain the product manager attribute parameters that affect the product manager's score, and the parameter values of the governing product attribute parameters, wherein the product manager attribute parameters include the product manager's age, graduation school, major, education, working time, etc., and the governing product attribute parameters include the net value growth rate and net value volatility of the product corresponding to the product manager. At the same time, information on other setting factors that affect the product net value other than the product manager can also be obtained.
[0139] S502: Inputting parameter values of setting parameters that affect the product manager's score into a pre-trained product manager's score determination model, and determining the product manager's score according to an output result of the product manager's score determination model.
[0140] S503: Input the product manager's score value and information of other set factors into the trained product net value prediction model, and obtain the product's net value prediction value based on the output result of the product net value prediction model.
[0141] For ease of understanding, the product net value prediction process provided by this application is explained below through a specific embodiment. Figure 6 , Figure 6A schematic diagram of a sixth product net value prediction process provided by some embodiments is shown, and the process includes the following steps:
[0142] S601: For any product to be predicted for net value, identify the product manager of the product, and obtain the parameter values of the risk resistance parameter, the product timing parameter, the profitability parameter, the product manager attribute parameter, and the parameter values of the governing product attribute parameters among the setting parameters that affect the product manager's score. Input the parameter values of the setting parameters that affect the product manager's score into the pre-trained product manager score determination model, and determine the product manager's score based on the output of the product manager score determination model. At the same time, information on other setting factors that affect the product's net value other than the product manager, such as product timing feature information, product basic feature information, and market factor information, can also be obtained.
[0143] S602: Input the product manager's score and information of other set factors into the trained product net value prediction model, and obtain the product's net value prediction value based on the output result of the product net value prediction model.
[0144] In a possible implementation, when the product manager's score and information of other set factors are input into the trained product net value prediction model, the embedding layer in the product net value prediction model can analyze and process the product time series feature information therein. In addition, the embedding layer in the product net value prediction model can also analyze and process information other than the product time series feature information, such as the product manager's score, basic feature information of the product, and market factor information. After using the transformer architecture to extract corresponding semantic features and other information from these information, the extracted information can be spliced (contact) with the product time series feature information processed by the embedding layer, and then the spliced information is analyzed and processed by a convolutional neural network (CNN) combined with a bidirectional long short-term memory neural network (BILSTM) to obtain a product net value prediction value, and output the net value prediction value (output).
[0145] The following is an introduction to the training process of the product manager rating value determination model.
[0146] When training a model for determining a product manager's rating value, any sample parameter value set in the sample set can be obtained. The sample parameter value set may include parameter values of several parameters. The sample parameter value set corresponds to a first sample label, and the first sample label is used to identify the product manager's rating value (initial rating value) corresponding to the sample parameter value set.
[0147] The acquired sample parameter value set can be input into the product manager score determination model to be trained, and the identification score value (for ease of description, referred to as the first identification label) corresponding to the sample parameter value set determined by the product manager score determination model can be obtained through the product manager score determination model to be trained. In a specific implementation, after the first identification label of the input sample parameter value set is determined, because the first sample label of the sample parameter value set is pre-saved, it is possible to determine whether the identification result of the product manager score determination model is accurate based on whether the first sample label is consistent with the first identification label. In a specific implementation, if they are inconsistent, it means that the identification result of the product manager score determination model is inaccurate, and the parameters of the product manager score determination model need to be adjusted to train the product manager score determination model.
[0148] In a specific implementation, when adjusting the parameters in the product manager rating value determination model, a gradient descent algorithm can be used to back-propagate the gradients of the parameters of the product manager rating value determination model, thereby training the product manager rating value determination model.
[0149] In a possible implementation, the above operation may be performed on each sample parameter value set in the sample set, and when a preset convergence condition is met, the product manager rating value is determined to indicate that model training is complete.
[0150] Among them, the preset convergence condition can be satisfied when the sample parameter value set in the sample set is determined by the original product manager score value determination model, the number of correctly identified sample parameter value sets is greater than the set number, or the number of iterations for training the product manager score value determination model reaches the set maximum number of iterations, etc. In the specific implementation, the setting can be flexibly made and is not specifically limited here.
[0151] In one possible implementation, when training a product manager rating value determination model, the sample parameter value set in the sample set can be divided into a training sample parameter value set and a test sample parameter value set. The product manager rating value determination model to be trained is first trained based on the training sample parameter value set, and then the reliability of the trained product manager rating value determination model is verified based on the test sample parameter value set.
[0152] The following is an introduction to the training process of the product net value prediction model.
[0153] When training the product net worth prediction model, any sample information in the sample set consisting of the product manager's score value and information of other set factors can be obtained. The sample information corresponds to a second sample label, and the second sample label is used to identify the product net worth prediction value corresponding to the sample information.
[0154] The acquired sample information can be input into the product net value prediction model to be trained, and the product net value prediction value determined by the product net value prediction model can be obtained through the product net value prediction model (referred to as the second identification label for ease of description). In a specific implementation, after the second identification label of the input sample information is determined, because the second sample label of the sample information is pre-saved, it is possible to determine whether the recognition result of the product net value prediction model is accurate based on whether the second sample label is consistent with the second identification label. In a specific implementation, if they are inconsistent, it means that the recognition result of the product net value prediction model is inaccurate, and it is necessary to adjust the parameters of the product net value prediction model to train the product net value prediction model.
[0155] In a specific implementation, when adjusting the parameters in the product net value prediction model, a gradient descent algorithm can be used to back-propagate the gradients of the parameters of the product net value prediction model, thereby training the product net value prediction model.
[0156] In a possible implementation, the above operation may be performed on each sample information in the sample set, and when a preset convergence condition is met, it is determined that the training of the product net value prediction model is completed.
[0157] Among them, the preset convergence condition can be satisfied when the sample information in the sample set passes through the original product net value prediction model, the number of sample information correctly identified is greater than the set number, or the number of iterations for training the product net value prediction model reaches the set maximum number of iterations, etc. In the specific implementation, it can be flexibly set and is not specifically limited here.
[0158] In one possible implementation, when training the product net worth prediction model to be trained, the sample information in the sample set can be divided into training sample information and test sample information. The original product net worth prediction model is first trained based on the training sample information, and then the reliability of the trained product net worth prediction model is verified based on the test sample information.
[0159] Embodiment 2:
[0160] Based on the same inventive concept, the present application provides a product net value prediction device, see Figure 7 , Figure 7 A schematic diagram of a product net value prediction device provided by some embodiments is shown, the device comprising:
[0161] The acquisition module 701 is used to identify the product manager of any product to be predicted for net value, obtain the parameter values of each setting parameter that affects the product manager's score value, input each parameter value into a pre-trained product manager score value determination model, and determine the product manager's score value according to the output result of the product manager score value determination model; and obtain information on other setting factors that affect the product's net value except the product manager;
[0162] The prediction module 702 is used to input the product manager's score value and the information of the other set factors into the trained product net value prediction model, and obtain the net value prediction value of the product according to the output result of the product net value prediction model.
[0163] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0164] If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager;
[0165] For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate;
[0166] For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score;
[0167] Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
[0168] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0169] If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score;
[0170] If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
[0171] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0172] If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score;
[0173] If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
[0174] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0175] The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
[0176] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0177] If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager;
[0178] Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
[0179] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0180] Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility;
[0181] The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
[0182] In a possible implementation manner, the acquisition module 701 is specifically configured to:
[0183] If the set parameters include profitability parameters, the yields of products of the various product strategies corresponding to the product manager are obtained;
[0184] The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
[0185] In a possible implementation, the setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, academic qualifications, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
[0186] Embodiment 3:
[0187] Based on the same inventive concept, on the basis of the above embodiments, the present application embodiment further provides an electronic device, which can realize the function of the product net value prediction device discussed above, please refer to Figure 8 , Figure 8 A schematic diagram of the structure of an electronic device provided in some embodiments is shown, the electronic device comprising: a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804;
[0188] The memory 803 stores a computer program. When the program is executed by the processor 801, the processor 801 performs the following steps:
[0189] For any product to be predicted for net worth, identify the product manager of the product, obtain the parameter values of each setting parameter that affects the product manager's score, input each parameter value into a pre-trained product manager score determination model, and determine the product manager's score according to the output result of the product manager score determination model; and obtain information on other setting factors that affect the product's net worth other than the product manager;
[0190] The product manager's score and the information of the other set factors are input into the trained product net value prediction model, and the net value prediction value of the product is obtained according to the output result of the product net value prediction model.
[0191] In a possible implementation manner, the processor 801 is specifically configured to:
[0192] If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager;
[0193] For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate;
[0194] For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score;
[0195] Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
[0196] In a possible implementation manner, the processor 801 is specifically configured to:
[0197] If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score;
[0198] If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
[0199] In a possible implementation manner, the processor 801 is specifically configured to:
[0200] If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score;
[0201] If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
[0202] In a possible implementation manner, the processor 801 is specifically configured to:
[0203] The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
[0204] In a possible implementation manner, the processor 801 is specifically configured to:
[0205] If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager;
[0206] Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
[0207] In a possible implementation manner, the processor 801 is specifically configured to:
[0208] Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility;
[0209] The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
[0210] In a possible implementation manner, the processor 801 is specifically configured to:
[0211] If the set parameters include profitability parameters, the yields of products of the various product strategies corresponding to the product manager are obtained;
[0212] The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
[0213] In a possible implementation, the setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, academic qualifications, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
[0214] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0215] The communication interface 802 is used for communication between the above electronic device and other devices.
[0216] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0217] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.
[0218] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, and a computer program product includes: a computer program code. When the computer program code runs on a computer, the computer executes any product net value prediction method discussed above, and the repeated parts are not repeated here.
[0219] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CD, DVD, BD, HVD, etc., and semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD), etc.
[0220] Based on the same inventive concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any product net value prediction method discussed above. Since the principle of solving the problem by the above computer program product is similar to that of the product net value prediction method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.
[0221] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0222] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0223] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0224] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0225] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A product net value prediction method, It is characterized in that The method comprises: For any product to be predicted for net worth, identify the product manager of the product, obtain the parameter values of each setting parameter that affects the product manager's score, input each parameter value into a pre-trained product manager score determination model, and determine the product manager's score according to the output result of the product manager score determination model; and obtain information on other setting factors that affect the product's net worth other than the product manager; The product manager's score and the information of the other set factors are input into the trained product net value prediction model, and the net value prediction value of the product is obtained according to the output result of the product net value prediction model.
2. The method according to claim 1, It is characterized in that The obtaining of parameter values of various setting parameters that affect the score value of the product manager includes: If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager; For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate; For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score; Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
3. The method according to claim 2, It is characterized in that The determining the first product performance score based on the second net worth growth rate and the first net worth growth rate includes: If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score; If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
4. The method according to claim 2, It is characterized in that The determining of the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate includes: If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score; If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
5. The method according to any one of claims 2 to 4, It is characterized in that The determining the second sub-selected product timing capability parameter value based on at least one of the first product performance score and the second product performance score comprises: The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
6. The method according to claim 1, It is characterized in that The obtaining of parameter values of various setting parameters that affect the score value of the product manager includes: If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager; Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
7. The method according to claim 6, It is characterized in that The step of determining the parameter value of the risk resistance parameter based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value includes: Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility; The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
8. The method according to claim 1, It is characterized in that The obtaining of parameter values of various setting parameters that affect the score value of the product manager includes: If the set parameters include profitability parameters, obtaining the yields of products of multiple product strategies corresponding to the product manager; The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
9. The method according to any one of claims 1 to 4, 6 to 8, It is characterized in that The setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, education level, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
10. A product net value prediction device, It is characterized in that The device comprises: An acquisition module is used to identify the product manager of any product for which net value prediction is to be performed, obtain parameter values of various setting parameters that affect the product manager's score value, input each of the parameter values into a pre-trained product manager score value determination model, and determine the product manager's score value according to the output result of the product manager score value determination model; and obtain information on various other setting factors that affect the product's net value in addition to the product manager; The prediction module is used to input the product manager's score value and the information of the other set factors into the trained product net value prediction model, and obtain the net value prediction value of the product according to the output result of the product net value prediction model.
11. The device according to claim 10, It is characterized in that The acquisition module is specifically used for: If the set parameters include a product selection timing capability parameter, identifying a target product whose sub-products are included in the product changed by the product manager; For each sub-product currently included in the target product, obtain the proportion of the sub-product in the target product and the sub-product net value growth rate of the sub-product; determine the timing ability parameter value of the first sub-selected product based on the product of the proportion of each sub-product and the sub-product net value growth rate; For the target product, determine the first net worth growth rate of the target product before the sub-product is changed, the second net worth growth rate after the sub-product is changed, and the third net worth growth rate of the product market as a whole within a set time; determine the first product performance score based on the values of the second net worth growth rate and the first net worth growth rate, and determine the second product performance score based on the values of the second net worth growth rate and the third net worth growth rate; determine the second sub-product timing ability parameter value based on at least one of the first product performance score and the second product performance score; Based on at least one of the first sub-product selection timing capability parameter value and the second sub-product selection timing capability parameter value, a parameter value of the product selection timing capability parameter is determined.
12. The device according to claim 11, It is characterized in that The acquisition module is specifically used for: If the second net worth growth rate and the first net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the first net worth growth rate is positive, the ratio of the second net worth growth rate to the first net worth growth rate is determined as the first product performance score; If the second net worth growth rate is a positive number and the first net worth growth rate is a negative number, the second net worth growth rate shall be determined as the first product performance score.
13. The device according to claim 11, It is characterized in that The acquisition module is specifically used for: If the second net worth growth rate and the third net worth growth rate are both positive or both negative, or if the second net worth growth rate is negative and the third net worth growth rate is positive, the ratio of the second net worth growth rate to the third net worth growth rate is determined as the second product performance score; If the second net worth growth rate is a positive number and the third net worth growth rate is a negative number, the second net worth growth rate shall be determined as the second product performance score.
14. The device according to any one of claims 11 to 13, It is characterized in that The acquisition module is specifically used for: The product of the first product performance score, the second product performance score and the set adjustment factor is determined as the second sub-product timing ability parameter value; wherein, when the second net worth growth rate is negative and the first net worth growth rate is positive and the third net worth growth rate is positive, the value of the adjustment factor is the set negative value; otherwise, the value of the adjustment factor is the set positive value.
15. The device according to claim 10, It is characterized in that The acquisition module is specifically used for: If the set parameters include a risk resistance parameter, obtain the first net asset value volatility of the product market as a whole within the set time, the second net asset value volatility of the product corresponding to the product manager, and the maximum drawdown index value of the product corresponding to the product manager; Based on the first net asset value volatility, the second net asset value volatility and the maximum drawdown index value, the parameter value of the risk resistance parameter is determined.
16. The device according to claim 15, It is characterized in that The acquisition module is specifically used for: Determining a third product performance score based on the values of the second net asset value volatility and the first net asset value volatility; The weighted sum of the third product performance score, the second net asset value volatility and the maximum drawdown index value is determined as the parameter value of the risk resistance parameter.
17. The device according to claim 10, It is characterized in that The acquisition module is specifically used for: If the set parameters include profitability parameters, obtaining the yields of products of multiple product strategies corresponding to the product manager; The parameter value of the profitability parameter is determined according to the weighted sum of the yields of products of multiple product strategies.
18. The device according to any one of claims 10-13, 15-17, It is characterized in that The setting parameters also include: at least one of a product manager attribute parameter and a jurisdiction product attribute parameter; wherein the product manager attribute parameter includes at least one of the product manager's age, graduation school, major, education level, working time, and gender; the jurisdiction product attribute parameter includes at least one of the net asset value growth rate and net asset value volatility of the product corresponding to the product manager.
19. An electronic device, It is characterized in that include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the steps included in any one of the methods of claims 1-9 according to the obtained program instructions.
20. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method according to any one of claims 1 to 9.
21. A computer program product, It is characterized in that The computer program product comprises: a computer program code, and when the computer program code is run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 9.
