CN116452339A

CN116452339A - Resource evaluation method and related product

Info

Publication number: CN116452339A
Application number: CN202210013907.6A
Authority: CN
Inventors: 伍沙沙; 傅桔选; 尹方亮; 贾玉博; 胡炘; 胡天行; 童炯潇
Original assignee: Tenpay Payment Technology Co Ltd
Current assignee: Tenpay Payment Technology Co Ltd
Priority date: 2022-01-06
Filing date: 2022-01-06
Publication date: 2023-07-18

Abstract

The application belongs to the technical field of computers, and particularly relates to a resource evaluation method and related products. The resource evaluation method comprises the following steps: acquiring net value data and bin holding data of the resource object in a historical time interval, wherein the net value data is used for representing the value amount of the resource object on each time node, and the bin holding data is used for representing asset configuration information of the resource object; performing category detection on the resource object according to the bin holding data to obtain a resource category to which the resource object belongs; extracting characteristics of the net value data and the bin holding data to obtain an evaluation score of the resource object, wherein the evaluation score is used for representing the profit prediction capability of the resource object in a future time interval; and sorting the resource objects in the resource category according to the evaluation score, and determining the evaluation grade of the resource objects according to the score sorting result. The method and the device can reduce the profit prediction difficulty of the resource object and improve the prediction accuracy and stability of future profit rate.

Description

Resource evaluation method and related product

Technical Field

The application belongs to the technical field of computers, and particularly relates to a resource evaluation method, a resource evaluation device, a computer readable medium, electronic equipment and a computer program product.

Background

There are various types of digital resources such as funds, stocks, etc. on the financial market, which can be used for investors to invest in order to increase their own profits. Each type of digital resource contains a large number of resource objects (e.g., a fund or stock) available for selection, and each resource object has a series of complex analytical data. In the face of analysis data with huge information, investors often have difficulty making correct financial decisions. Therefore, how to effectively integrate analysis data, so as to reduce the learning cost and decision cost of investors is a problem to be solved at present.

Disclosure of Invention

The present application aims to provide a resource evaluation method, a resource evaluation device, a computer-readable medium, an electronic device, and a computer program product, which at least overcome to some extent the technical problems of complex analysis data, high learning cost, high decision cost, and the like in investment decisions of resource objects.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned in part by the practice of the application.

According to an aspect of the embodiments of the present application, there is provided a resource evaluation method, including:

Acquiring net value data and bin holding data of a resource object in a historical time interval, wherein the net value data is used for representing the value amount of the resource object on each time node, and the bin holding data is used for representing asset configuration information of the resource object;

performing category detection on the resource object according to the bin holding data to obtain a resource category to which the resource object belongs;

extracting characteristics of the net value data and the bin holding data to obtain an evaluation score of the resource object, wherein the evaluation score is used for representing the profit prediction capability of the resource object in a future time interval;

and carrying out score sorting on the resource objects in the resource category according to the evaluation scores, and determining the evaluation grades of the resource objects according to the score sorting results.

According to an aspect of the embodiments of the present application, there is provided a resource evaluation device, including:

the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is configured to acquire net value data and storage data of a resource object in a historical time interval, the net value data is used for representing the value amount of the resource object on each time node, and the storage data is used for representing asset configuration information of the resource object;

The detection module is configured to detect the category of the resource object according to the bin holding data to obtain the resource category to which the resource object belongs;

the extraction module is configured to perform feature extraction on the net value data and the bin holding data to obtain an evaluation score of the resource object, wherein the evaluation score is used for representing the profit prediction capability of the resource object in a future time interval;

and the sorting module is configured to sort the resource objects in the resource category according to the evaluation scores, and determine the evaluation grades of the resource objects according to the score sorting results.

According to an aspect of the embodiments of the present application, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a resource evaluation method as in the above technical solution.

According to an aspect of the embodiments of the present application, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the resource assessment method as in the above technical solution via execution of the executable instructions.

According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the resource evaluation method as in the above technical solution.

In the technical scheme provided by the embodiment of the application, the bin holding data of the resource object is obtained, and the bin holding data can be classified according to the bin holding data, so that the resource object can be sequenced according to the profit predictability and the profit stability under the same resource category, the evaluation grade of the resource object is determined according to the sequencing result, the similar comparison scoring is carried out based on the same risk profit level, the profit prediction difficulty of the resource object can be reduced, and the prediction accuracy and the prediction stability of the future profit rate are improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

Fig. 1 shows a block diagram of an exemplary system architecture to which the technical solution of the present application is applied.

FIG. 2 illustrates a flow chart of steps of a resource assessment method in one embodiment of the present application.

FIG. 3 illustrates a flowchart of steps for feature extraction of equity data and taken in a holding data in one embodiment of the present application.

Fig. 4 shows a schematic block diagram of obtaining an evaluation index in an embodiment of the present application.

FIG. 5 shows a flowchart of the steps for screening for an evaluation factor in one embodiment of the present application.

FIG. 6 illustrates a portion of tabular data for screening net worth factors in one application scenario in accordance with an embodiment of the present application.

Fig. 7 shows a portion of table data for screening a binning factor in an application scenario according to an embodiment of the present application.

FIG. 8 is a flowchart illustrating the steps of weighting fusion of integration factors in one embodiment of the present application.

Fig. 9 shows an effect diagram of selecting different weighting policies in an application scenario according to an embodiment of the present application. FIG. 9A shows the distribution effect and the relevant characterization parameters of the simulation evaluation score obtained by performing factor weighted fusion by using an IR weighted model; FIG. 9B shows the distribution effect and related characterization parameters of the simulated evaluation score obtained by factor weighted fusion using a fixed weight model.

Fig. 10 shows an effect diagram of selecting different bin frequencies in an application scenario according to an embodiment of the present application. Wherein, fig. 10A shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every quarter bin adjustment, fig. 10B shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every half year bin adjustment, and fig. 10C shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every year bin adjustment.

FIG. 11 shows a histogram of relevant characterization parameters and the ratio of the summer coefficients of the relevant characterization parameters obtained by rating bond-type funds in one application scenario according to the embodiment of the present application.

FIG. 12 is a diagram showing the effect of a review of a monetary fund rating in one application scenario in accordance with an embodiment of the present application.

Fig. 13 schematically shows a block diagram of the resource evaluation device provided in the embodiment of the present application.

Fig. 14 schematically illustrates a block diagram of a computer system suitable for use in implementing embodiments of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

In particular embodiments of the present application, related data relating to user information, investment information, etc., when various embodiments of the present application are applied to particular products or technologies, user permissions or consents need to be obtained, and the collection, use, and processing of related data need to comply with relevant laws and regulations and standards of the relevant countries and regions.

Related terms related to the technical scheme of the present application are explained as follows.

Information coefficient (Information Coefficient, IC): IC represents the correlation between predicted and realized values, and is typically used to evaluate predictive capabilities (e.g., stock selection capabilities). The larger the IC absolute value, the better the predictive power.

Information ratio (Information Ratio, IR): the method is obtained by calculating the ratio of the multicycle mean value of the IC to the standard deviation of the IC and is used for judging the stability of the IC, namely the stability of the predictive capability. IR gives consideration to both the factor's stock selection ability and the factor's stock selection ability stability, and the larger the IR value, the better.

Yield Analysis (Return Analysis): the method mainly refers to a hierarchical backtracking method, factor data are arranged according to numerical value size sequence, are divided into a plurality of groups and then are subjected to backtracking, and a simulated net value curve and performance index of each group are calculated.

Monotonicity: the factor data is ranked from big to small to obtain a factor ranking value, then the evaluation parameter ranking value is obtained based on the evaluation parameter ranking from big to small, and the rank correlation between the evaluation parameter and the factor data is calculated; the closer the absolute value of the rank correlation is to 100%, the more pronounced the monotonicity is.

As shown in fig. 1, system architecture 100 may include a terminal device 110, a network 120, and a server 130. Terminal device 110 may include various electronic devices such as smart phones, tablet computers, notebook computers, desktop computers, and the like. The server 130 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, and may be, for example, a wired communication link or a wireless communication link.

The system architecture in the embodiments of the present application may have any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 130 may be a server group composed of a plurality of server devices. In addition, the technical solution provided in the embodiment of the present application may be applied to the terminal device 110, or may be applied to the server 130, or may be implemented by the terminal device 110 and the server 130 together, which is not limited in particular in this application.

For example, the server 130 may monitor various types of digital resources in the financial market in real time, and periodically acquire and analyze data to obtain an evaluation level for the resource object. The server 130 may push the evaluation level of the resource object to the terminal device 110 through the network 120, or the terminal device 110 may actively pull the evaluation level of the resource object obtained by the data analysis by the server 130. The investor can obtain the evaluation levels of various resource objects by using the terminal device 110, so that corresponding investment decisions can be made according to the evaluation levels.

It should be noted that, the embodiments of the present application are described with funds as the main resource types, but the present application may also be applicable to various investment objects such as stocks, futures, etc. in practical application scenarios, and the present application is not limited thereto.

The following describes in detail the resource evaluation method, the resource evaluation device, the computer readable medium, the electronic device, the computer program product, and other technical schemes provided in the present application with reference to the specific embodiments.

Fig. 2 shows a flowchart of steps of a resource evaluation method in an embodiment of the present application, where the resource evaluation method may be performed by the terminal device 110 or the server 130 shown in fig. 1, or may be performed by the terminal device 110 and the server 130 together. As shown in fig. 2, the resource evaluation method in the embodiment of the present application may mainly include the following steps S210 to S240.

Step S210: acquiring net value data and bin holding data of the resource object in a historical time interval, wherein the net value data is used for representing the value amount of the resource object on each time node, and the bin holding data is used for representing asset configuration information of the resource object;

step S220: performing category detection on the resource object according to the bin holding data to obtain a resource category to which the resource object belongs;

step S230: extracting characteristics of the net value data and the bin holding data to obtain an evaluation score of the resource object, wherein the evaluation score is used for representing the profit predictability and the profit stability of the resource object in a future time interval;

step S240: and sorting the resource objects in the resource category according to the evaluation score, and determining the evaluation grade of the resource objects according to the score sorting result.

In the resource evaluation method provided by the embodiment of the application, the bin holding data of the resource object is obtained, and the bin holding data can be classified according to the bin holding data, so that the resource object can be sequenced according to the profit predictability and the profit stability under the same resource category, the evaluation grade of the resource object is determined according to the sequencing result, the similar comparison scoring is carried out based on the same risk profit level, the profit prediction difficulty of the resource object can be reduced, and the prediction accuracy and the prediction stability of the future profit rate are improved.

The following describes in detail the respective method steps of the resource evaluation method.

In step S210, net worth data of the resource object in the historical time interval is obtained, the net worth data being used to represent the value amounts of the resource object on the respective time nodes, and bin holding data being used to represent asset configuration information of the resource object.

The resource object is a business object related to an investment business of a user in a financial market, may include a digital resource as an investment target of a fund, a bond, a stock, etc., and may also include a business entity for investment management of the digital resource, such as a fund manager or a fund company. The present application is described in various embodiments primarily as a public recruitment fund (Public Offering of Fund), which refers to a securities investment fund that recruits funds to the public investors in a public manner and targets securities as the primary investment. The public recruitment funds are recruited by a mass spreading means, and sponsors collect public funds to set up investment funds for security investment. These funds are under strict supervision of law and have industry specifications such as information disclosure, profit sharing, operation restriction, etc.

Equity data is used to represent the value of a resource object at various time nodes, e.g., equity data for a fund refers to the equity value of the fund, i.e., the total equity value calculated from trading market equity on each business day, based on all equity owned by the fund, after deducting various costs and fees on the day of the fund. In short, the net value of the fund is the balance of the total market value of the asset minus the liabilities at a certain point. The net value of the fund represents the equity of the fund holder, i.e., the investor. Generally, the net value of funds is divided into a unit net value and an accumulated net value. The net per unit is the sales price of the funds, which is = (total assets-total liabilities)/total number of shares of the funds. The total assets of the fund refers to the total amount of assets calculated by the equity price of all assets (including stocks, bonds, bank deposits, other securities, etc.) owned by the fund. The total liabilities of the funds refer to liabilities formed during the operation and financing of the funds, including payouts to escrow or manager, payouts, and the like.

The holding data is used to represent asset configuration information of the resource object, for example, the holding data of the fund includes all the assets owned by the fund and the proportion of each asset, for example, stocks, bonds, bank deposits, other securities, and the like.

In step S220, the class detection is performed on the resource object according to the bin holding data, so as to obtain the resource class to which the resource object belongs.

Different resource categories represent different levels of risk benefit, and the effectiveness of the assessment can be guaranteed only by comparing resource objects with the same risk benefit features. At present, the classification granularity of the license is too coarse, the classification granularity of the data quotient is too fine, and unreasonable classification exists in some types, such as flexibly configured funds, stock holding of some funds is more than 80%, stock holding of other funds is about 20%, and effective comparison is generally difficult under different risk and income levels. Therefore, the embodiment of the application penetrates through the foundation bottom layer to hold the warehouse on the basis of the secondary classification of the data quotient source concentration, and the resource classification is carried out according to the investment standard.

In one embodiment of the present application, the resource category to which the resource object belongs may be determined according to a relationship between the share ratio of each asset in the holding data and a preset proportion threshold. For example, the embodiments of the present application may divide funds into three categories, stock-type funds, bond-type funds, and balance-type funds according to the holding data. Wherein, stock-type funds refer to funds with the underlying share holding bin holding more than 60% in consecutive quarters, bond-type funds refer to funds with the underlying bond holding bin holding more than 60% in consecutive quarters, and balanced-type funds refer to funds with the underlying share holding bin and the underlying bond holding bin both below 60% in consecutive quarters.

In step S230, feature extraction is performed on the net worth data and the bin holding data to obtain an evaluation score of the resource object, where the evaluation score is used to represent the profit prediction capability of the resource object in the future time interval.

The profit prediction capability may include prediction accuracy and prediction stability of the profit rate, and the higher the evaluation score, the stronger the profit prediction capability of the resource object in the future time interval, that is, the resource profit rate in the future time interval can be accurately and stably predicted.

FIG. 3 illustrates a flowchart of steps for feature extraction of equity data and taken in a holding data in one embodiment of the present application. As shown in fig. 3, on the basis of the above embodiment, the feature extraction of the net value data and the holding data in step S230 to obtain the evaluation score of the resource object may include the following steps S310 to S330.

In step S310, an evaluation index for performing feature evaluation on the equity data and the hand-over data is acquired.

In one embodiment of the present application, a net value evaluation index for performing feature evaluation on net value data and a holding bin evaluation index for performing feature evaluation on holding bin data may be respectively acquired, where the net value evaluation index includes at least one of a benefit class index, a risk adjustment benefit class index, or a stability index, and the holding bin evaluation index includes at least one of an asset configuration index, an industry configuration index, or a performance attribution index.

Fig. 4 shows a schematic block diagram of obtaining an evaluation index in an embodiment of the present application. As shown in fig. 4, in the embodiments of the present application, for a fund object, feature evaluations may be performed from two evaluation dimensions of performance scoring system 410 and configuration behavior feature 420.

The performance scoring system 410 may further include four valuation sub-dimensions for describing capacity, namely, profitability 411, risk resistance 412, cost performance 413, and stability 414; configuration behavior feature 420 may further include configuration capability 421, stock capability 422, and timing capability 423 for a total of three evaluation sub-dimensions for describing capability.

For each evaluation sub-dimension, an evaluation index for performing feature evaluation may be acquired separately. Each evaluation sub-dimension corresponding to the performance scoring system 410 may obtain a corresponding net worth evaluation index. As shown in FIG. 4, the profitability 411 corresponds to a profitability class indicator, the anti-risk capability 412 corresponds to a risk class indicator, the cost of investment 413 corresponds to a risk adjustment profitability class indicator, and the stability 414 corresponds to a stability indicator.

Each evaluation sub-dimension corresponding to the configuration behavior feature 420 may obtain a corresponding out-of-bin evaluation index. As shown in fig. 4, the configuration capability 421 corresponds to an asset configuration index and an industry configuration index, the stock selection capability 422 corresponds to a performance attribution index, and the timing capability 423 also corresponds to a performance attribution index.

In step S320, an evaluation factor for predicting the resource yield of the resource object in the future time interval is screened according to the evaluation index.

In one embodiment of the present application, the evaluation factors include a net value factor corresponding to the net value data and a taken in factor corresponding to the taken in data.

FIG. 5 shows a flowchart of the steps for screening for an evaluation factor in one embodiment of the present application. As shown in fig. 5, on the basis of the above embodiment, the screening of the evaluation factors for predicting the resource profitability of the resource object in the future time interval according to the evaluation index in step S320 may include the following steps S510 to S550.

Step S510: and drawing a net value curve of the resource object according to the net value data, wherein the net value curve is used for representing the mapping relation between the value amount of the resource object and the time sequence.

The value amount of a resource object may be represented by a net value of the resource. Equity may also be referred to as depreciated value, meaning the balance of the original value of a fixed asset or the reset full value minus the cumulative depreciated amount. The net value reflects the current value of the original resource object after a certain period of time has elapsed, i.e., the actual amount of funds occupied.

Taking stock as an example, stock net total = company fund + method fixed principal + capital principal + special principal + cumulative surplus-cumulative deficit; equity = equity total per total number of shares issued.

As can be seen from the formulas, the net stock value represents the owned funds and the rights enjoyed by stakeholders in common. The net value of the stock has close relation with the true value and the market value of the stock. The absolute value of the stock represents the management and financial conditions of the past year of the company, so the absolute value of the stock can be used as a main basis for measuring and calculating the true value of the stock. If the net value of a certain stock is high, the running financial condition of the company is good, the equity enjoyed by stakeholders is more, the future profit capability of the stock is strong, the true value of the stock is higher, and the market value is also increased; and vice versa. Compared with the stock true value and the market value, the stock net value is more exact and reliable, because the net value is calculated according to the existing financial statement, the data on which the net value is based is quite specific and exact, and the credibility is high; meanwhile, the net value can clearly reflect the accumulated results of the company's annual operation; the net value is also relatively fixed and typically varies only when the final surplus is charged or the company is funded. Therefore, the net stock value has higher authenticity, accuracy and stability, can be used as an important basis for selecting a issuing mode and determining an issuing price when a company issues stocks, and is also a main parameter of investment analysis.

Taking the fund as an example, continuously monitoring the net value of the fund and drawing a time sequence curve to obtain a corresponding net value curve. The net curve may represent the benefit, volatility, maximum withdrawal, and the rate of the summer, etc. of the foundation (or strategy).

Step S520: a net factor associated with the net worth evaluation index is extracted from the net worth curve.

The net factor is an indicator derived from the net time series. Through the net value curve, a large number of net value factors can be extracted from the dimensions of the profit class index, the risk adjustment profit class index, the net value-based model and the like. For example, the revenue class factors corresponding to the revenue class indicators may include interval profitability, alpha, homonym ranking, profitability, and the like; risk class factors corresponding to the risk class indicators may include volatility, maximum withdrawal, downstream standard deviation, etc.; the risk-adjusted benefit factors corresponding to the risk-adjusted benefit-class indicators may include a summer ratio, a kama ratio, a proposed no ratio, an informative ratio, a reynolds ratio, and so forth. In addition to net factors related to risk and revenue, stock factors, timing factors, style factors, such as barrera factors, etc., representing the ability of the foundation manager may be included.

Step S530: and collecting public information of the resource object according to the holding data, wherein the public information is used for periodically disclosing the asset configuration information of the resource object.

The public information of the fund can comprise, for example, quarter financial report, half-year financial report, year financial report and the like, and further can comprise periodic disclosure information for related objects such as a fund manager, a fund company and the like.

Step S540: and extracting the bin holding factors associated with the bin holding evaluation indexes from the public information.

The holding factors are factors which penetrate through the foundation bed assets and are extracted according to the characteristics of the foundation product bed holding targets, such as the belonging industry, the large-class asset configuration and the like. The retention factors may include, for example, retention concentration, value factor, growth factor, stock right bin (retention ratio), bin volatility, retention mobility, industry stability, industry concentration, industry contribution, and the like. The holding factor is related to the asset information of the fund and can be measured and calculated in a rolling way according to a preset period (such as a quarter or half year).

Step S550: and carrying out validity verification on the net value factor and the bin holding factor to screen an evaluation factor for predicting the resource yield of the resource object in a future time interval according to a verification result.

In one embodiment of the present application, a method of validating a net worth factor and a taken place factor may include: selecting at least one prediction node and at least one prediction interval taking the prediction node as a time starting point in the historical time interval; determining a resource yield corresponding to the prediction interval according to the net value data in the prediction interval; and taking the resource yield as a prediction target, and acquiring a correlation parameter of the net value factor or the bin holding factor at the prediction node and the resource yield, wherein the correlation parameter is used for representing the prediction effectiveness of the net value factor or the bin holding factor.

In one embodiment of the present application, a method for selecting at least one prediction node in a historical time interval and at least one prediction interval with the prediction node as a time starting point may include: acquiring a sliding window with a specified length and a sliding step length corresponding to the sliding window; moving the sliding window in the history interval according to the sliding step length to obtain a plurality of rolling periods; and selecting a prediction node according to the rolling period and taking the prediction node as a prediction interval of a time starting point.

For example, the embodiment of the present application may move the sliding window according to a sliding step (such as a quarter or half year) in the historical time interval, so as to slide and select the predicted node, and determine a rolling period with the predicted node as a time starting point, where one rolling period corresponds to one predicted interval. The interval length of the prediction interval may be, for example, one quarter, half year or one year. For the selected prediction interval, the corresponding resource yield can be determined according to the net value data in the prediction interval, and then the net value factor or the correlation parameter of the bin holding factor and the resource yield at the prediction node is obtained by taking the resource yield as a prediction target.

In one embodiment of the present application, the correlation parameters may include an information coefficient IC for representing predictability of the net factor or the taken factor and an information ratio IR for representing predicted stability of the net factor or the taken factor.

Information coefficient IC represents the correlation between predicted and realized values and is typically used to evaluate predictive capabilities (e.g., stock selection capabilities). The larger the absolute value of the information coefficient, the better the predictive power. The information ratio IR is obtained by calculating a ratio of the multicycle mean value of the information coefficient to the standard deviation of the information coefficient, and is used for judging the stability of the information coefficient, namely the stability of the predictive power. The information ratio IR gives consideration to both the factor stock selection capability and the factor stock selection capability stability, and the larger the information ratio IR is, the better the value is.

FIG. 6 illustrates a portion of tabular data for screening net worth factors in one application scenario in accordance with an embodiment of the present application. The application scene is mainly used for verifying the validity of factors by an information analysis method and a yield analysis method, 7-year period data from 7 months 1 in 2010 to 6 months 30 in 2017 are used as factor measurement data, and the factors pass through complete cattle Xiong Zhouqi according to quarterly rolling measurement and calculation for 28 periods in total.

As shown in fig. 6, the annual rate of return fannual_rr_2y_last of the last 2 years is best predicted and stable. The information coefficient IC is close to 10%, indicating good predictability. The information ratio ICIR is greater than 1, indicating that there is a stable ability to acquire excess revenue. In addition, the annual gain rate fannual_rr_1y_last of the recent 1 year and the annual gain rate fannual_rr_3y_last of the recent 3 years also have good prediction effects. Wherein, the prediction index frr_1y_future represents the future 1 year rate of return, frr_2y_future represents the future 2 year rate of return, frr_3m_future represents the future 1 quarter rate of return, and frr_6m_future represents the future half year rate of return.

Fig. 7 shows a portion of table data for screening a binning factor in an application scenario according to an embodiment of the present application. The factors shown in fig. 7 are taken to be taken factors related to taken data of fund shares, equity, etc. For monetary funds, the fund scale has good predictive power and predictive power is also stable. This is financial logic compliant because the size is very important for money market funds, and for large-scale and small-scale money market funds, it is difficult to guarantee their liquidity for large-scale and small-scale institutional investors. And the investment of a single investment in and out has great influence on the investment of managers, and the investment can possibly cause huge redemption to delay payment and easily cause the serious fluctuation of the income.

In step S330, the evaluation factors are weighted and fused to obtain an evaluation score of the resource object.

In one embodiment of the present application, before the evaluation factors are weighted and fused, the evaluation factors may be further ranked according to the numerical value; and then, carrying out standardization processing on the ordered evaluation factors to obtain the evaluation factors with values within a set numerical range. For example, if the numerical range is set to 0-100, all the evaluation factors can be subjected to numerical allocation again according to the sorting result, so that the factor values obtained by allocation are distributed within the range of 0-100, and no extreme value exists. In addition, in the case where there is a data loss in the evaluation factor, the value thereof may be configured by default to set the median of the numerical range so as to represent a median value level.

In one embodiment of the present application, a method for performing weighted fusion on an evaluation factor may include: acquiring an information ratio for representing the prediction stability of the evaluation factor; weighting and fusing the evaluation factors corresponding to the same evaluation index according to the information ratio to obtain an integration factor; and carrying out weighted fusion on the integration factors corresponding to the different evaluation indexes to obtain the evaluation score of the resource object.

In the embodiment of the present application, for the evaluation factors corresponding to the same evaluation index (for example, the evaluation factors determined according to different prediction intervals), the information ratio is used as the weight to perform weighted summation, so as to obtain the corresponding integration factor. And then continuously weighting and fusing the integration factors corresponding to different evaluation indexes to finally obtain the evaluation score of the resource object.

FIG. 8 is a flowchart illustrating the steps of weighting fusion of integration factors in one embodiment of the present application. As shown in fig. 8, the method of weighting and fusing the integration factors to obtain the evaluation score may include the following steps S810 to S850 on the basis of the above embodiments.

Step S810: a plurality of contribution weights corresponding to the integration factor are obtained, and the contribution weights are used for representing the contribution degree of the integration factor to the resource yield rate in the predicted future time interval.

In one embodiment of the present application, different weighted fusion strategies may be employed to obtain multiple contribution weights. The embodiment of the application can perform linear regression on the integration factor to obtain the first contribution degree weight of the integration factor. For example, a linear regression may be performed using a common least squares method (Ordinary Least Square, OLS) to fit the resulting linear regression coefficients as the first contribution weights. The core idea of the least squares method is to estimate by minimizing the sum of squares of the residuals.

The embodiment of the application can also acquire the information ratio corresponding to the integration factor, and take the information ratio as the second contribution degree weight of the integration factor. The information ratio corresponding to the integration factor may be predicted from the information ratio of each evaluation factor, for example, may be an average information ratio of each evaluation factor.

The embodiment of the application may further obtain a preset fixed weight, and use the fixed weight as the third contribution weight of the integration factor. In the case where the individual integration factors have the same fixed weight, the contribution of all the integration factors to the lower-stage yield is the same.

Step S820: and respectively carrying out weighted fusion on the integration factors by using the weights of the multiple contribution degrees to obtain the simulation evaluation score of the resource object.

And respectively carrying out weighted fusion on the integration factors by using a plurality of different contribution weights, so that the simulation evaluation scores of the resource objects under different contribution prediction models can be obtained. For example, after the integration factors are weighted and fused by using the first contribution weight, the second contribution weight, and the third contribution weight determined in step S810, a first simulation evaluation score based on the OLS linear regression model, a second simulation evaluation score based on the IR weighted model, and a third simulation evaluation score based on the fixed weight model may be obtained.

Step S830: and sequencing the resource objects in the resource category according to the simulated evaluation score, and predicting a monotonicity parameter of the simulated evaluation score according to the sequencing result, wherein the monotonicity parameter is used for representing a rating layering effect of rating the resource objects according to the simulated evaluation score.

In one embodiment of the present application, a method for predicting monotonicity parameters of a simulated evaluation score based on ranking results may include: determining a simulation sorting value of the simulation evaluation score according to the sorting result; acquiring a risk benefit factor of the resource object, wherein the risk benefit factor is used for representing the benefit rate of the resource object after risk adjustment; ordering the risk benefit factors to obtain factor ordering values of the risk benefit factors; and determining the monotonicity parameter of the simulation evaluation score according to the rank correlation of the simulation ranking value and the factor ranking value.

In one embodiment of the present application, the risk benefit factor may be, for example, a sharp Ratio (shappe Ratio), which is the average of the net growth rate of the fund minus the risk-free rate divided by the standard deviation of the net growth rate of the fund. The summer ratio reflects the extent to which the net rate of increase of the unit risk fund exceeds the no risk rate of return. If the summer ratio is positive, the average net growth rate of the funds exceeds the risk-free interest rate during the measuring period, and the investment funds are better than the bank deposit under the condition that the same-period bank deposit interest rate is taken as the risk-free interest rate. The greater the summer ratio, the higher the risk return that is obtained for the unit risk of the fund.

According to the embodiment of the application, the simulation ranking value can be determined according to the ranking result of the simulation evaluation score, meanwhile, the factor ranking value of the shap ratio can be obtained after the shap ratio is ranked, and then the monotonicity parameter of the simulation evaluation score is determined according to the rank correlation of the two ranking values. The closer the monotonicity parameter is to 100%, the more pronounced the monotonicity is.

Step S840: and selecting the target contribution degree weight with the best grading and layering effects according to the monotonicity parameter.

Fig. 9 shows an effect diagram of selecting different weighting policies in an application scenario according to an embodiment of the present application. FIG. 9A shows the distribution effect and the relevant characterization parameters of the simulation evaluation score obtained by performing factor weighted fusion by using an IR weighted model; FIG. 9B shows the distribution effect and related characterization parameters of the simulated evaluation score obtained by factor weighted fusion using a fixed weight model. Wherein, the parameter group represents the fund grouping, the parameter return_rate represents the interval profitability, the parameter volatibility represents the interval fluctuation rate, the parameter maxdrowdown represents the maximum withdrawal, the parameter sharp_rate represents the summer rate, and the parameter annu_return_rate represents the annual profitability.

In the application scenario, after the stock type fund pool is constructed and the funds under the resource category are scored and sequenced, the stock type fund pool can be divided into five scoring grades, namely, all the funds are divided into five groups, G1 is the group with the highest scoring, and G5 is the group with the lowest scoring. The historical time interval of data acquisition is from 1 day of 7 months in 2017 to 30 days of 6 months in 2020, and rolling and bin adjustment are carried out by taking half a year as a period.

As can be seen from comparing fig. 9A and 9B, the fixed weight model has a better layering effect than the IR weighted model. Therefore, the embodiment of the application can select the contribution degree weight obtained based on the fixed weight model as the target contribution degree weight.

Step S850: and carrying out weighted fusion on the integration factors corresponding to the different evaluation indexes according to the target contribution degree weight to obtain the target evaluation score of the resource object.

After the target contribution degree weight is determined by using the weighting model with the best layering effect, the integration factors can be weighted and fused according to the target contribution degree weight, and finally the target evaluation score of the resource object is obtained. According to the method and the device, different bin adjustment frequencies can be adopted for adjusting the foundation pool, so that the target evaluation scores of the resource objects are dynamically updated in different bin adjustment periods.

In step S240, the resource objects are score-ranked in the resource category according to the evaluation score, and the evaluation level of the resource objects is determined according to the score ranking result.

The embodiment of the application may divide the resource objects in one resource category into a plurality of evaluation levels, for example, five groups shown in fig. 9 correspond to five evaluation levels.

In one embodiment of the present application, the bin allocation frequency may be adjusted, so that an appropriate bin allocation evaluation rate is selected as an evaluation period of resource grouping evaluation.

Fig. 10 shows an effect diagram of selecting different bin frequencies in an application scenario according to an embodiment of the present application. Wherein, fig. 10A shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every quarter bin adjustment, fig. 10B shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every half year bin adjustment, and fig. 10C shows the distribution effect and the related characterization parameters of the simulated evaluation score obtained according to the bin adjustment frequency of once every year bin adjustment. Based on the comparison of fig. 10A, 10B and 10C, the quaternary bin adjustment layering effect is the best, and the quaternary bin adjustment has obvious monotonicity, so that the bin adjustment frequency of once each quaternary bin adjustment can be selected to update the rank of the funds in the fund pool.

FIG. 11 shows a histogram of relevant characterization parameters and the ratio of the summer coefficients of the relevant characterization parameters obtained by rating bond-type funds in one application scenario according to the embodiment of the present application. As shown in the figure, the degree of distinction between the G1 group and the G2 group is not high from the viewpoint of the interval return rate and the sharp ratio, but the overall has a good layering effect.

Fig. 12 shows a diagram of a return effect of grading monetary funds in an application scenario, where monotonicity corresponding to each grading is obvious, which indicates that the resource evaluation method provided by the embodiment of the present application has extremely high accuracy and stability.

It should be noted that although the steps of the methods in the present application are depicted in the accompanying drawings in a particular order, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

The following describes an embodiment of an apparatus of the present application, which may be used to perform the resource evaluation method in the above embodiment of the present application. Fig. 13 schematically shows a block diagram of the resource evaluation device provided in the embodiment of the present application. As shown in fig. 13, the resource evaluation device 1300 may mainly include:

an acquisition module 1310 configured to acquire net value data of a resource object in a historical time interval and bin holding data, wherein the net value data is used for representing a value amount of the resource object on each time node, and the bin holding data is used for representing asset configuration information of the resource object;

A detection module 1320, configured to perform category detection on the resource object according to the holding data, so as to obtain a resource category to which the resource object belongs;

an extraction module 1330 configured to perform feature extraction on the equity data and the out-of-bin data to obtain an evaluation score for the resource object, the evaluation score being used to represent a revenue prediction capability of the resource object over a future time interval;

a ranking module 1340 configured to rank the resource objects in the resource categories according to the ranking scores and to determine a ranking of the resource objects according to the ranking scores.

In one embodiment of the present application, based on the above embodiment, the extracting module 1330 may further include:

an index acquisition module 1331 configured to acquire an evaluation index for performing feature evaluation on the net value data and the holding data;

a factor screening module 1332 configured to screen, according to the rating index, a rating factor for predicting a resource yield of the resource object in a future time interval;

and a factor fusion module 1333 configured to perform weighted fusion on the evaluation factors to obtain an evaluation score of the resource object.

In one embodiment of the present application, based on the above embodiments, the index obtaining module 1331 may be further configured to: acquiring a net value evaluation index for performing feature evaluation on the net value data and a holding evaluation index for performing feature evaluation on the holding data, wherein the net value evaluation index comprises at least one of a benefit class index, a risk adjustment benefit class index or a stability index, and the holding evaluation index comprises at least one of an asset configuration index, an industry configuration index or a performance attribution index.

In one embodiment of the present application, based on the above embodiments, the evaluation factors include a net value factor corresponding to the net value data and a taken-in factor corresponding to the taken-in data; factor screening module 1332 may further include:

a net value curve drawing module configured to draw a net value curve of the resource object according to the net value data, wherein the net value curve is used for representing a mapping relation between a value amount of the resource object and a time sequence;

a net factor extraction module configured to extract a net factor associated with the net evaluation index from the net curve;

The public information acquisition module is configured to acquire public information of the resource object according to the warehouse-holding data, wherein the public information is used for periodically disclosing information of asset configuration information of the resource object;

a binning factor extraction module configured to extract a binning factor associated with the binning evaluation index from the public information;

and the validity verification module is configured to perform validity verification on the net value factor and the bin holding factor so as to screen an evaluation factor for predicting the resource yield of the resource object in a future time interval according to a verification result.

In one embodiment of the present application, based on the above embodiments, the validity verification module may be further configured to: selecting at least one prediction node and at least one prediction interval taking the prediction node as a time starting point in the historical time interval; determining a resource yield corresponding to the prediction interval according to the net value data in the prediction interval; and taking the resource yield as a prediction target, and acquiring a correlation parameter of a net value factor or a bin holding factor at the prediction node and the resource yield, wherein the correlation parameter is used for representing the prediction effectiveness of the net value factor or the bin holding factor.

In one embodiment of the present application, based on the above embodiments, the correlation parameter includes an information coefficient for representing predictability of the net value factor or the taken-up factor and an information ratio for representing predicted stability of the net value factor or the taken-up factor.

In one embodiment of the present application, based on the above embodiments, the validity verification module may be further configured to: acquiring a sliding window with a specified length and a sliding step length corresponding to the sliding window; moving the sliding window in the history interval according to the sliding step length to obtain a plurality of rolling periods; and selecting a prediction node according to the rolling period and taking the prediction node as a prediction interval of a time starting point.

In one embodiment of the present application, based on the above embodiments, the extracting module 1330 may further include: a factor ranking module configured to rank the evaluation factors by numerical magnitude; and the factor standardization module is configured to carry out standardization processing on the sorted evaluation factors to obtain the evaluation factors with values within a set numerical range.

In one embodiment of the present application, based on the above embodiments, the factor fusion module 1333 may further include:

an information ratio acquisition module configured to acquire an information ratio representing a predicted stability of the evaluation factor;

the factor integration module is configured to perform weighted fusion on the evaluation factors corresponding to the same evaluation index according to the information ratio to obtain an integration factor;

and the factor weighting module is configured to carry out weighted fusion on the integration factors corresponding to different evaluation indexes to obtain the evaluation score of the resource object.

In one embodiment of the present application, based on the above embodiments, the factor weighting module may further include:

a contribution weight acquisition module configured to acquire a plurality of contribution weights corresponding to the integration factor, the contribution weights being used to represent a degree of contribution of the integration factor to a resource yield within a predicted future time interval;

the contribution weight weighting module is configured to respectively use the plurality of contribution weights to carry out weighted fusion on the integration factors so as to obtain the simulation evaluation score of the resource object;

the simulation ordering module is configured to order the resource objects in the resource category according to the simulation evaluation score, and predict monotonicity parameters of the simulation evaluation score according to the ordering result, wherein the monotonicity parameters are used for representing the grading layering effect of grading the resource objects according to the simulation evaluation score;

The target weight selection module is configured to select the target contribution degree weight with the best grading and layering effects according to the monotonicity parameter;

and the target weighting module is configured to carry out weighted fusion on the integration factors corresponding to the different evaluation indexes according to the target contribution degree weight to obtain the target evaluation score of the resource object.

In one embodiment of the present application, based on the above embodiments, the contribution weight-obtaining module may be further configured to: performing linear regression on the integration factors to obtain first contribution weights of the integration factors; acquiring an information ratio corresponding to the integration factor, and taking the information ratio as a second contribution weight of the integration factor; and acquiring a preset fixed weight, and taking the fixed weight as a third contribution weight of the integration factor.

In one embodiment of the present application, based on the above embodiments, the analog sequencing module may be further configured to: determining a simulation sorting value of the simulation evaluation score according to the sorting result; acquiring a risk benefit factor of the resource object, wherein the risk benefit factor is used for representing the benefit rate of the resource object after risk adjustment; sorting the risk benefit factors to obtain factor sorting values of the risk benefit factors; and determining the monotonicity parameter of the simulation evaluation score according to the rank correlation of the simulation ranking value and the factor ranking value.

Specific details of the resource evaluation device provided in each embodiment of the present application have been described in detail in the corresponding method embodiments, and are not described herein again.

Fig. 14 schematically shows a block diagram of a computer system for implementing an electronic device according to an embodiment of the present application.

It should be noted that, the computer system 1400 of the electronic device shown in fig. 14 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 14, the computer system 1400 includes a central processing unit 1401 (Central Processing Unit, CPU) that can execute various appropriate actions and processes according to a program stored in a Read-Only Memory 1402 (ROM) or a program loaded from a storage section 1408 into a random access Memory 1403 (Random Access Memory, RAM). In the random access memory 1403, various programs and data necessary for the system operation are also stored. The cpu 1401, the rom 1402, and the ram 1403 are connected to each other via a bus 1404. An Input/Output interface 1405 (Input/Output interface, i.e., I/O interface) is also connected to bus 1404.

The following components are connected to the input/output interface 1405: an input section 1406 including a keyboard, a mouse, and the like; an output portion 1407 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker; a storage section 1408 including a hard disk or the like; and a communication section 1409 including a network interface card such as a local area network card, a modem, and the like. The communication section 1409 performs communication processing via a network such as the internet. The drive 1410 is also connected to the input/output interface 1405 as needed. Removable media 1411, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memory, and the like, is installed as needed on drive 1410 so that a computer program read therefrom is installed as needed into storage portion 1408.

In particular, according to embodiments of the present application, the processes described in the various method flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 1409 and/or installed from the removable medium 1411. The computer programs, when executed by the central processor 1401, perform the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal that propagates in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for evaluating resources, comprising:

2. The resource assessment method according to claim 1, wherein performing feature extraction on the net worth data and the holding data comprises:

acquiring an evaluation index for performing characteristic evaluation on the net value data and the bin holding data;

screening an evaluation factor for predicting the resource return rate of the resource object in a future time interval according to the evaluation index;

And carrying out weighted fusion on the evaluation factors to obtain the evaluation score of the resource object.

3. The resource evaluation method according to claim 2, wherein acquiring an evaluation index for performing feature evaluation on the net worth data and the holding data comprises:

acquiring a net value evaluation index for performing feature evaluation on the net value data and a holding evaluation index for performing feature evaluation on the holding data, wherein the net value evaluation index comprises at least one of a benefit class index, a risk adjustment benefit class index or a stability index, and the holding evaluation index comprises at least one of an asset configuration index, an industry configuration index or a performance attribution index.

4. The resource assessment method according to claim 3, wherein the assessment factors include a net value factor corresponding to the net value data and a taken-in factor corresponding to the taken-in data; screening the evaluation factors for predicting the resource return rate of the resource object in a future time interval according to the evaluation indexes, wherein the evaluation factors comprise:

drawing a net value curve of the resource object according to the net value data, wherein the net value curve is used for representing the mapping relation between the value amount of the resource object and the time sequence;

Extracting a net factor associated with the net evaluation index from the net curve;

acquiring public information of the resource object according to the warehouse holding data, wherein the public information is used for periodically disclosing asset configuration information of the resource object;

extracting a bin holding factor associated with the bin holding evaluation index from the public information;

and carrying out validity verification on the net value factor and the bin holding factor to screen an evaluation factor for predicting the resource yield of the resource object in a future time interval according to a verification result.

5. The resource assessment method according to claim 4, wherein validating the net value factor and the taken-up factor comprises:

selecting at least one prediction node and at least one prediction interval taking the prediction node as a time starting point in the historical time interval;

determining a resource yield corresponding to the prediction interval according to the net value data in the prediction interval;

and taking the resource yield as a prediction target, and acquiring a correlation parameter of a net value factor or a bin holding factor at the prediction node and the resource yield, wherein the correlation parameter is used for representing the prediction effectiveness of the net value factor or the bin holding factor.

6. The resource evaluation method according to claim 5, wherein the correlation parameter includes an information coefficient for representing predictability of the net value factor or the taken-up factor and an information ratio for representing predicted stability of the net value factor or the taken-up factor.

7. The resource evaluation method according to claim 5, wherein selecting at least one predicted node and at least one predicted interval with the predicted node as a time start point in the historic time interval comprises:

acquiring a sliding window with a specified length and a sliding step length corresponding to the sliding window;

moving the sliding window in the history interval according to the sliding step length to obtain a plurality of rolling periods;

and selecting a prediction node according to the rolling period and taking the prediction node as a prediction interval of a time starting point.

8. The resource evaluation method according to any one of claims 2 to 7, characterized in that before the weighted fusion of the evaluation factors, the method further comprises:

sorting the evaluation factors according to the numerical values;

And (3) carrying out standardization treatment on the ordered evaluation factors to obtain the evaluation factors with values within a set numerical range.

9. The resource evaluation method according to any one of claims 2 to 7, characterized in that weighting fusion is performed on the evaluation factors, comprising:

acquiring an information ratio representing the predicted stability of the evaluation factor;

weighting and fusing the evaluation factors corresponding to the same evaluation index according to the information ratio to obtain an integration factor;

and carrying out weighted fusion on the integration factors corresponding to the different evaluation indexes to obtain the evaluation score of the resource object.

10. The resource evaluation method according to claim 9, wherein weighting and fusing the integration factors corresponding to the different evaluation indexes includes:

obtaining a plurality of contribution weights corresponding to the integration factors, wherein the contribution weights are used for representing the contribution degree of the integration factors to the resource yield rate in a predicted future time interval;

respectively weighting and fusing the integration factors by using the multiple contribution weights to obtain a simulation evaluation score of the resource object;

sorting the resource objects in the resource category according to the simulation evaluation score, and predicting monotonicity parameters of the simulation evaluation score according to the sorting result, wherein the monotonicity parameters are used for representing grading layering effects of grading the resource objects according to the simulation evaluation score;

Selecting a target contribution degree weight with the best grading and layering effects according to the monotonicity parameters;

and weighting and fusing integration factors corresponding to different evaluation indexes according to the target contribution degree weight to obtain the target evaluation score of the resource object.

11. The resource evaluation method according to claim 10, wherein acquiring a plurality of contribution weights corresponding to the integration factor comprises:

performing linear regression on the integration factors to obtain first contribution weights of the integration factors;

acquiring an information ratio corresponding to the integration factor, and taking the information ratio as a second contribution weight of the integration factor;

and acquiring a preset fixed weight, and taking the fixed weight as a third contribution weight of the integration factor.

12. The resource evaluation method according to claim 10, wherein predicting the monotonicity parameter of the simulated evaluation score based on the ranking result comprises:

determining a simulation sorting value of the simulation evaluation score according to the sorting result;

acquiring a risk benefit factor of the resource object, wherein the risk benefit factor is used for representing the benefit rate of the resource object after risk adjustment;

Sorting the risk benefit factors to obtain factor sorting values of the risk benefit factors;

and determining the monotonicity parameter of the simulation evaluation score according to the rank correlation of the simulation ranking value and the factor ranking value.

13. A resource evaluation device, comprising:

14. A computer readable medium, characterized in that the computer readable medium has stored thereon a computer program which, when executed by a processor, implements the resource assessment method according to any one of claims 1 to 12.

15. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to cause the electronic device to perform the resource assessment method of any one of claims 1 to 12 via execution of the executable instructions.

16. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the resource assessment method according to any one of claims 1 to 12.