A project recommendation method and system

Abstract

An embodiment of the present application discloses a project recommendation method and system. The method includes: obtaining project data related to a target user and corresponding benchmark data; the project data includes combined data; performing attribution decomposition based on the combined data and the benchmark data to obtain the industry configuration contribution and individual selection contribution of each project; respectively ranking based on the industry configuration contribution and individual selection contribution of all projects, and screening out projects that meet the set conditions for recommendation to the target user. Efficiently calculate the configuration contribution and individual selection contribution of projects, and accurately recommend projects.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of data processing, and in particular to a project recommendation method and system. Background Art

[0002] With the rapid development of the economy, a large amount of transaction data is generated in commodity transactions and big data transactions. There is an increasing demand for screening the explosively growing transaction data and making accurate recommendations according to user needs. Among the massive data, actively recommending associated transaction data that is consistent with the possible needs of users according to user preferences can greatly improve the efficiency of users' data acquisition.

[0003] The trading operations of the trading system continue, constantly generating new transaction data and benchmark data, and it is necessary to modify the associated recommendation strategy for each project. However, the accuracy and efficiency of existing recommendation systems are relatively low. Summary of the Invention

[0004] Therefore, embodiments of the present application provide a project recommendation method and system, which can efficiently count the configuration contribution and individual selection contribution of projects and accurately recommend projects.

[0005] To achieve the above object, embodiments of the present application provide the following technical solutions:

[0006] According to a first aspect of embodiments of the present application, a project recommendation method is provided, and the method includes:

[0007] Obtain project data related to a target user and corresponding benchmark data; the project data includes combined data;

[0008] Perform attribution decomposition based on the combined data and the benchmark data to obtain the industry configuration contribution and individual selection contribution of each project;

[0009] Rank based on the industry configuration contribution and individual selection contribution of all projects respectively, and screen out projects that meet the set conditions to recommend to the target user.

[0010] Optionally, performing attribution decomposition based on the combined data and the benchmark combined data to obtain the industry configuration contribution and individual selection contribution of each project includes:

[0011] Based on the weights and contributions of each project in the combination and the weights and contributions of each project in the benchmark combination, calculate the industry configuration contribution and individual selection contribution of each project according to the attribution model.

[0012] Optionally, based on the weights and contributions of each project in the combination and the weights and contributions of each project in the benchmark combination, calculate the industry configuration contribution of each project according to the following formula:

[0013]

[0014] Among them, AR t is the industry allocation contribution at time t, and k t and k are adjustment factors, which are calculated according to the following formulas respectively:

[0015]

[0016]

[0017] Among them, R pt is the single-period portfolio contribution, and R bt is the single-period benchmark portfolio contribution.

[0018] Optionally, the industry allocation contribution is specifically calculated according to the following formula:

[0019]

[0020] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; w i,b is the weight of the benchmark industry in the benchmark portfolio, and r i,b is the weight of the target industry in the benchmark portfolio.

[0021] Optionally, based on the attribution model, according to the weights and contributions of each item in the portfolio and the weights and contributions of each item in the benchmark portfolio, the individual selection contribution of each item is calculated, and is calculated according to the following formula:

[0022]

[0023] Among them, SR t is the individual selection contribution at time t, and k t and k are adjustment factors.

[0024] Optionally, the individual selection contribution is specifically calculated according to the following formula:

[0025]

[0026] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; r i,b is the weight of the target industry in the benchmark portfolio.

[0027] Optionally, after obtaining the project data related to the target user and the corresponding benchmark data, the method further includes:

[0028] Classify the project data and the corresponding benchmark data according to preset rules to obtain the types of the project data and the corresponding benchmark data respectively.

[0029] Determine the attribution model according to the types.

[0030] According to the second aspect of the embodiments of the present application, a project recommendation system is provided. The system includes:

[0031] A data acquisition module for acquiring project data related to a target user and the corresponding benchmark data; the project data includes portfolio data.

[0032] A performance attribution module for performing attribution decomposition according to the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project.

[0033] A project recommendation module for ranking respectively based on the industry allocation contribution and individual selection contribution of all projects, and screening out projects that meet the set conditions to recommend to the target user.

[0034] According to the third aspect of the embodiments of the present application, an electronic device is provided, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor runs the computer program, it is configured to implement the method described in the first aspect above.

[0035] According to the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement the method described in the first aspect above.

[0036] In summary, the embodiments of the present application provide a project recommendation method and system. By acquiring project data related to a target user and the corresponding benchmark data; the project data includes portfolio data; performing attribution decomposition according to the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project; ranking respectively based on the industry allocation contribution and individual selection contribution of all projects, and screening out projects that meet the set conditions to recommend to the target user. It efficiently counts the configuration contribution and individual selection contribution of projects and accurately recommends projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other implementation drawings can be obtained based on the provided drawings without creative efforts.

[0038] The structures, ratios, sizes, etc. illustrated in this specification are only used to match the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the implementation conditions of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0039] Figure 1 It is a schematic flowchart of a project recommendation method provided by an embodiment of this application;

[0040] Figure 2 It is a block diagram of a project recommendation system provided by an embodiment of this application;

[0041] Figure 3 It shows a schematic structural diagram of an electronic device provided by an embodiment of this application;

[0042] Figure 4 It shows a schematic diagram of a computer-readable storage medium provided by an embodiment of this application. Specific embodiments

[0043] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in this technology can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.

[0044] Figure 1 It shows a project recommendation method provided by an embodiment of this application, and the method includes:

[0045] Step 101: Obtain project data related to the target user and corresponding reference data; the project data includes combined data, and the reference data includes reference combined data;

[0046] Step 102: Perform attribution decomposition based on the combined data and the reference combined data to obtain the industry configuration contribution and individual selection contribution of each project;

[0047] Step 103: Rank respectively based on the industry configuration contributions and individual selection contributions of all projects, and screen out projects that meet the set conditions for recommendation to the target user.

[0048] In a possible implementation manner, in step 102, performing attribution decomposition based on the combined data and the reference combined data to obtain the industry configuration contribution and individual selection contribution of each project includes:

[0049] Based on the weights and contributions of each item in the said portfolio and the weights and contributions of each item in the benchmark portfolio, and based on the attribution model, calculate the industry allocation contribution and individual selection contribution of each item.

[0050] In a possible implementation manner, based on the weights and contributions of each item in the said portfolio and the weights and contributions of each item in the benchmark portfolio, and based on the attribution model, calculate the industry allocation contribution of each item, and calculate according to the following formula:

[0051]

[0052] where, AR t is the industry allocation contribution at time t, k t and k are adjustment factors, and are calculated respectively according to the following formulas:

[0053]

[0054]

[0055] where, R pt is the single-period portfolio contribution, R bt is the single-period benchmark portfolio contribution.

[0056] In a possible implementation manner, the industry allocation contribution is specifically calculated according to the following formula:

[0057]

[0058] where, w i,p is the weight of the target industry in the portfolio, r i,p is the weight of the target industry in the portfolio; w i,b is the weight of the benchmark industry in the benchmark portfolio, r i,b is the weight of the target industry in the benchmark portfolio.

[0059] In a possible implementation manner, based on the weights and contributions of each item in the said portfolio and the weights and contributions of each item in the benchmark portfolio, and based on the attribution model, calculate the individual selection contribution of each item, and calculate according to the following formula:

[0060]

[0061] where, SR t is the individual selection contribution at time t, k t and k are adjustment factors.

[0062] In a possible implementation manner, the individual selection contribution is specifically calculated according to the following formula:

[0063]

[0064] Among them, w i,p is the weight of the target industry in the portfolio, r i,p is the weight of the target industry in the portfolio; r i,b is the weight of the target industry in the benchmark portfolio.

[0065] In a possible implementation manner, after obtaining the project data related to the target user and the corresponding benchmark data in step 101, the method further includes:

[0066] Classify the project data and the corresponding benchmark data according to a preset rule to obtain the types of the project data and the corresponding benchmark data respectively; determine an attribution model according to the types.

[0067] In a possible implementation manner, the preset rule may include the relationships between each classification level and classifications, and any classification level may include at least one next classification level of any classification level.

[0068] Performance attribution analysis is to quantitatively decompose the actual performance of a portfolio into various influencing factors. The essence of performance attribution analysis is to compare the actual performance of a project portfolio with the contribution of a market benchmark (Benchmark), and at the same time, decompose the difference between the two into several "effects", such as allocation effect and individual selection effect.

[0069] Most of the attributions in the prior art are single-period Brinson models for single-category projects, and different benchmarks are selected, and the attribution results obtained from different benchmarks are very different. For many projects, it is inconvenient to view the contribution levels of sub-projects, the benchmarks, and the benchmark contribution degrees. And in project recommendations, it is rare to see recommendation results attributed according to each sub-project, industry, and stock.

[0070] The Brinson model is the most commonly used performance decomposition model. The single-period Brinson model means that the investment manager has no transactions during this period, and there is no cash inflow and outflow. The single-period Brinson model can analyze the performance of a project in each period and decompose it into allocation contribution, individual selection contribution, and interaction contribution. However, if the project manager keeps adjusting positions and needs to evaluate the source of the excess contribution of this project at the end of the year, the single-period Brinson model is no longer applicable at this time. To evaluate this year, the multi-period Brinson model can be used. In actual investment, due to the operations of the investment manager and the inflow and outflow of external cash flows, the industry allocation weights often change.

[0071] However, the configuration contribution, individual selection contribution, and interaction contribution cannot simply add up the configuration contributions for each month. Since the total contribution of the project portfolio minus the total contribution of the benchmark is not equal to the sum of the differences between the portfolio contributions and the benchmark contributions for each period, a new algorithm is needed to solve this problem.

[0072] The following further describes the application method of the project recommendation method provided in the embodiments of the present application when applied in the financial field.

[0073] In the first aspect, data processing is mainly divided into three types.

[0074] A: Analyze the project fund data to obtain the stock and bond composition information corresponding to the daily valuation table portfolio.

[0075] B: Obtain the stock and bond composition information in the public offering of funds according to the public offering fund composition table. A public offering of funds is a securities investment fund that raises funds from the general public investors in an open manner and mainly invests in securities. Public offering of funds is recruited by means of mass communication. The sponsor pools public funds to establish an investment fund for securities investment. These funds are under strict legal supervision and have industry norms such as information disclosure, profit distribution, and operation restrictions.

[0076] C: Obtain the benchmark data corresponding to the fund, such as ten benchmarks including the CSI 300, China Securities Index, China Bond Index, Shanghai Composite Index, and Shanghai 100 Index.

[0077] In actual application, the portfolio return corresponding to the investment portfolio constructed by the user, consisting of investment targets such as stocks, bonds, and funds, is the investment return obtained from the investment of the investment portfolio over a period compared with the initial investment. For example, capital gains, dividend income, interest income, etc. Furthermore, in the present application, portfolio data can be used to refer to data related to the investment portfolio constructed by the user. For example, the investment portfolio specifically composed of which investment targets (stocks, bonds, funds, etc.), the purchase ratio of each investment target, and information such as capital gains, dividend income, and interest income over a period.

[0078] The benchmark portfolio data can refer to an investment portfolio determined by selecting an index or a composite index in the market. For example, a market index that can represent the average performance of a certain market, such as a stock index like the CSI 300. Furthermore, in the present application, the benchmark portfolio data can be used to refer to data related to the public market. Among them, the benchmark portfolio data can include the investment portfolio specifically composed of which investment targets (stocks, bonds, funds, etc.), the purchase ratio of each investment target, and information such as capital gains, dividend income, and interest income over a period.

[0079] The structure of the benchmark portfolio is the same as that of the investment portfolio, that is, it has the same first-level asset classification, second-level asset classification, and each asset. The difference is that each asset in the benchmark portfolio is represented by a specific benchmark index, which can be a market index or a composite index composed of market index composite operations. The weights of each asset in the benchmark portfolio can also be different from those of the investment portfolio.

[0080] Second, portfolio attribution.

[0081] Use CSI 300, China Bond Total Index, money fund index, and CSI 300*60%-China Bond Total Index*40% as the industries in the attribution. The weights can be set by the customer themselves. The benchmark is obtained by combining based on the weights set by the customer for CSI 300, China Bond Total Index, money fund index, and CSI 300*60%-China Bond Total Index*40%.

[0082] As components of stocks and bonds, sub-funds use an algorithm similar to the multi-period Brinson attribution to obtain the results of the performance attribution decomposition of the corresponding sub-funds: industry allocation contribution and individual stock selection contribution.

[0083] Among them, the industry allocation contribution can specifically see the specific contribution values in CSI 300, China Bond Total Index, money fund index, and CSI 300*60%-China Bond Total Index*40%. The individual stock selection contribution can also see the specific contribution rate of return on a certain sub-fund, so that the Top sub-funds in the fund can be seen.

[0084] Investment decisions include: industry allocation and individual stock selection, and industry allocation is determined prior to individual stock selection, which conforms to most investment decision-making processes and there is no interaction term.

[0085] Third, Brinson attribution in sub-funds.

[0086] For each sub-fund, further attribution analysis can be carried out according to the corresponding benchmark to obtain the contributions of each sub-fund in the corresponding industry and stock selection. Brinson attribution is a class of models that attribute the performance of funds based on position data and can decompose the sources of excess returns of single-period or multi-period funds. In the embodiments of the present application, the excess return of the benchmark is decomposed into asset allocation return (AR), individual stock selection return (SR), and interaction return (IR). The return other than the asset allocation return (AR) and the individual stock selection return (SR) is called the interaction return (IR).

[0087] The return of asset allocation can be understood as being able to clearly see the strength trends of major asset classes and being able to judge which asset classes will have relatively high returns in the future, that is, the return obtained by allocating the investment proportions among various asset classes. The return of individual stock selection can be understood as whether it is possible to select assets in the stock market and bond market that have higher returns than the market benchmark, that is, the return obtained by selecting individual types of assets under the same capital allocation ratio. The interaction return can refer to the return jointly generated by asset allocation and individual stock selection.

[0088] A: Single-period Brinson attribution: Single-period assumes that the investment manager has no transactions during this period and no cash inflows and outflows.

[0089] Excess return of the investment portfolio:

[0090]

[0091] Among them, w i,p is the weight of a certain industry in the investment portfolio, and r i,p is the weight of a certain industry in the investment portfolio; w i,b is the weight of the benchmark industry in the benchmark portfolio, and r i,b is the weight of a certain industry in the benchmark portfolio.

[0092] Industry allocation contribution:

[0093]

[0094] Individual stock selection contribution:

[0095]

[0096] (Using the weights of the investment portfolio)

[0097] It can be proved that: TR = AR + SR.

[0098] The allocation weights of each industry in the portfolio during the above single-period model remain unchanged. However, in actual investment, due to the operations of the investment manager and the inflows and outflows of external cash flows, the industry allocation weights often change. Therefore, it is necessary to construct a multi-period Brinson model.

[0099] For a real investment portfolio, single-period Brinson attribution can be carried out for each trading day. However, once it comes to attribution within a certain time interval, there will be problems with the changes in the weights of assets or individual stocks within the interval, and it is necessary to generalize the single-period Brinson model to a multi-period Brinson model.

[0100] B: Multi-period Brinson attribution:

[0101] Industry allocation contribution:

[0102]

[0103] Individual stock selection contribution:

[0104]

[0105] where k t and k are adjustment factors, and the specific calculation formulas are as follows:

[0106]

[0107]

[0108] R pt corresponds to the single-period portfolio return, and R bt corresponds to the single-period benchmark return.

[0109] Fourth aspect, fund recommendation.

[0110] Based on the above attribution results, for fund managers or individual users, they can directly recommend funds to target users according to the contribution of the funds, ranked by industry contribution or by individual stock contribution.

[0111] The embodiment of the present application also provides a performance attribution method, and the performance attribution method includes the following steps:

[0112] Step 1: Obtain project data related to the target user and the corresponding benchmark data; the project data includes portfolio data, and the benchmark data includes benchmark portfolio data;

[0113] Step 2: Perform attribution decomposition according to the portfolio data and the benchmark portfolio data to obtain the industry allocation contribution and individual selection contribution of each project;

[0114] In a possible implementation manner, after obtaining the project data related to the target user and the corresponding benchmark data, the method further includes: classifying the project data and the corresponding benchmark data according to a preset rule to obtain the types of the project data and the corresponding benchmark data respectively; determining an attribution model according to the types.

[0115] In a possible implementation manner, in step 2, performing attribution decomposition according to the portfolio data and the benchmark portfolio data to obtain the industry allocation contribution and individual selection contribution of each project includes:

[0116] Calculating the industry allocation contribution and individual selection contribution of each project based on the attribution model according to the weights and contributions of the projects in the portfolio and the weights and contributions of the projects in the benchmark portfolio.

[0117] In a possible implementation, based on the weights and contributions of the items in the combination and the weights and contributions of the items in the benchmark combination according to the attribution model, the industry allocation contribution of each item is calculated as follows:

[0118]

[0119] Among them, AR t is the industry allocation contribution at time t, and k t and k are adjustment factors, which are calculated according to the following formulas respectively:

[0120]

[0121]

[0122] Among them, R pt is the single-period portfolio contribution, and R bt is the single-period benchmark portfolio contribution.

[0123] In a possible implementation, the industry allocation contribution is specifically calculated according to the following formula:

[0124]

[0125] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; w i,b is the weight of the benchmark industry in the benchmark portfolio, and r i,b is the weight of the target industry in the benchmark portfolio.

[0126] In a possible implementation, based on the weights and contributions of the items in the combination and the weights and contributions of the items in the benchmark combination according to the attribution model, the individual selection contribution of each item is calculated as follows:

[0127]

[0128] Among them, SR t is the individual selection contribution at time t, and k t and k are adjustment factors.

[0129] In a possible implementation, the individual selection contribution is specifically calculated according to the following formula:

[0130]

[0131] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; ri,b is the weight of the target industry in the benchmark portfolio.

[0132] In summary, the embodiment of the present application provides a project recommendation method, which obtains project data related to a target user and corresponding benchmark data; the project data includes portfolio data; performs attribution decomposition based on the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project; ranks based on the industry allocation contribution and individual selection contribution of all projects respectively, and filters out projects that meet the set conditions to recommend to the target user. It efficiently calculates the allocation contribution and individual selection contribution of projects and accurately recommends projects.

[0133] Based on the same technical concept, the embodiment of the present application also provides a project recommendation system, as Figure 2 shown, the system includes:

[0134] A data acquisition module 201, configured to obtain project data related to a target user and corresponding benchmark data; the project data includes portfolio data;

[0135] A performance attribution module 202, configured to perform attribution decomposition based on the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project;

[0136] A project recommendation module 203, configured to rank based on the industry allocation contribution and individual selection contribution of all projects respectively, and filter out projects that meet the set conditions to recommend to the target user.

[0137] In a possible implementation manner, the performance attribution module 202 is specifically configured to:

[0138] Based on the attribution model, calculate the industry allocation contribution and individual selection contribution of each project according to the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio.

[0139] In a possible implementation manner, based on the attribution model, calculate the industry allocation contribution of each project according to the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio, and calculate according to the following formula:

[0140]

[0141] where, AR t is the industry allocation contribution at time t, k t and k are adjustment factors, and are calculated according to the following formulas respectively:

[0142]

[0143]

[0144] Among them, R pt is the contribution of a single - period portfolio, and R bt is the contribution of the single - period benchmark portfolio.

[0145] In a possible implementation manner, the industry allocation contribution is specifically calculated according to the following formula:

[0146]

[0147] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; w i,b is the weight of the benchmark industry in the benchmark portfolio, and r i,b is the weight of the target industry in the benchmark portfolio.

[0148] In a possible implementation manner, based on the attribution model, according to the weights and contributions of each item in the portfolio and the weights and contributions of each item in the benchmark portfolio, the individual selection contribution of each item is calculated, and is calculated according to the following formula:

[0149]

[0150] Among them, SR t is the individual selection contribution at time t, and k t and k are adjustment factors.

[0151] In a possible implementation manner, the individual selection contribution is specifically calculated according to the following formula:

[0152]

[0153] Among them, w i,p is the weight of the target industry in the portfolio, and r i,p is the weight of the target industry in the portfolio; r i,b is the weight of the target industry in the benchmark portfolio.

[0154] In a possible implementation manner, the system further includes:

[0155] An attribution model determination module, configured to classify the project data and the corresponding benchmark data according to a preset rule to obtain the types of the project data and the corresponding benchmark data respectively; and determine an attribution model according to the types.

[0156] In a possible implementation manner, the preset rule may include the relationship between each classification level and the classification, and any classification level may include at least one next classification level of any classification level.

[0157] In a possible implementation, the preset rules can be divided into two ways: "bottom-up" and "top-down". Specifically, the "bottom-up" way is simply to obtain the securities that meet the rules for upward hierarchical aggregation, that is, to set label rules, and the lower layers that meet the rule settings will enter the upper layer for aggregation. The "top-down" way is simply to filter and screen the upper layer for lower layer analysis, that is, to classify the upper layer pool according to rules, and those that do not meet the requirements are classified as others. The difference between the "bottom-up" and "top-down" lies in that the "bottom-up" is screened according to what the user cares about, constructing a new combination pool, while the "top-down" way is to classify and analyze all from the perspective of company management. In actual application, based on the needs of different users, it can be specifically selected whether to adopt the "bottom-up" preset classification rules or the "top-down" preset classification rules.

[0158] The embodiments of the present application also provide an electronic device corresponding to the method provided in the foregoing embodiments. Please refer to Figure 3 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. The electronic device 20 may include: a processor 200, a memory 201, a bus 202, and a communication interface 203. The processor 200, the communication interface 203, and the memory 201 are connected through the bus 202; a computer program that can run on the processor 200 is stored in the memory 201, and when the processor 200 runs the computer program, it executes the method provided in any of the foregoing embodiments of the present application.

[0159] Among them, the memory 201 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one physical port 203 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0160] The bus 202 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 201 is used to store programs. After receiving the execution instruction, the processor 200 executes the program, and the method disclosed in any of the foregoing embodiments of the present application can be applied to the processor 200 or implemented by the processor 200.

[0161] The processor 200 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 200 or the instructions in the form of software. The above-mentioned processor 200 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and combines its hardware to complete the steps of the above method.

[0162] The electronic device provided by the embodiment of the present application and the method provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by it.

[0163] The embodiment of the present application also provides a computer-readable storage medium corresponding to the method provided by the foregoing embodiment. Please refer to Figure 4 , which shows that the computer-readable storage medium is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by the processor, it will execute the method provided by any of the foregoing embodiments.

[0164] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here one by one.

[0165] The computer-readable storage medium provided by the above embodiment of the present application and the method provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored in it.

[0166] It should be noted that:

[0167] The algorithms and displays provided herein are not inherently related to any particular computer, virtual apparatus, or other device. Various general-purpose apparatuses may also be used in conjunction with the teachings presented herein. The structure required to construct such apparatuses will be apparent from the above description. In addition, the present application is not directed to any particular programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the description of a particular language above is for the purpose of disclosing the best mode of the present application.

[0168] In the specification provided herein, a number of specific details are set forth. However, it is understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0169] Similarly, it should be understood that, in order to streamline the present application and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed present application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate embodiment of the present application.

[0170] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0171] In addition, those skilled in the art can understand that although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of this application and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0172] Each component embodiment of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation device according to the embodiments of the present application. The present application can also be implemented as a device or device program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0173] It should be noted that the above embodiments illustrate rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0174] As described above, only the preferred specific embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed claims.

Claims

1. A project recommendation method, characterized in that, the method includes: Obtaining project data related to the target user and corresponding benchmark data; the project data includes portfolio data; Performing attribution decomposition based on the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project; Ranking based on the industry allocation contributions and individual selection contributions of all projects respectively, and screening out projects that meet the set conditions for recommending to the target user; The performing attribution decomposition based on the portfolio data and the benchmark portfolio data to obtain the industry allocation contribution and individual selection contribution of each project includes: calculating the industry allocation contribution and individual selection contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to an attribution model; wherein, calculating the industry allocation contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to the attribution model is calculated according to the following formula: Among them, is the industry allocation contribution at time t, and k are adjustment factors, which are calculated according to the following formulas respectively: Among them, is the contribution of a single-period portfolio, is the contribution of a single-period benchmark portfolio; Calculating the individual selection contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to the attribution model is calculated according to the following formula: wherein, is the individual selection contribution at time t, and k is an adjustment factor.

2. The method according to claim 1, characterized in that, the industry allocation contribution is specifically calculated according to the following formula: Among them, is the weight of the target industry in the portfolio, is the weight of the target industry in the portfolio; is the weight of the benchmark industry in the benchmark portfolio, is the weight of the target industry in the benchmark portfolio.

3. The method according to claim 1, characterized in that, the individual selection contribution is specifically calculated according to the following formula: Among them, is the weight of the target industry in the portfolio, is the weight of the target industry in the portfolio; is the weight of the target industry in the benchmark portfolio.

4. The method according to claim 1, characterized in that, after obtaining the project data related to the target user and the corresponding benchmark data, the method further includes: Classifying the project data and the corresponding benchmark data according to a preset rule to obtain the types of the project data and the corresponding benchmark data respectively; Determining an attribution model according to the type.

5. A project recommendation system, characterized in that, the system includes: A data acquisition module for obtaining project data related to the target user and corresponding benchmark data; the project data includes portfolio data; A performance attribution module for performing attribution decomposition based on the portfolio data and the benchmark data to obtain the industry allocation contribution and individual selection contribution of each project; the performing attribution decomposition based on the portfolio data and the benchmark portfolio data to obtain the industry allocation contribution and individual selection contribution of each project includes: calculating the industry allocation contribution and individual selection contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to an attribution model; wherein, calculating the industry allocation contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to the attribution model is calculated according to the following formula: Among them, is the industry allocation contribution at time t, and k are adjustment factors, which are calculated according to the following formulas respectively: Among them, is the contribution of a single-period portfolio, is the contribution of a single-period benchmark portfolio; Calculating the individual selection contribution of each project based on the weights and contributions of each project in the portfolio and the weights and contributions of each project in the benchmark portfolio according to the attribution model is calculated according to the following formula: wherein, is the individual selection contribution at time t, and k is an adjustment factor; A project recommendation module, which is used to rank based on the industry configuration contribution and individual selection contribution of all projects respectively, and screen out projects that meet the set conditions to recommend to the target user.

6. An electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor runs the computer program, it is executed to implement the method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1-4.

Images