CN112330022A - Asset allocation weight determination method based on electric power big data and related equipment thereof - Google Patents

Asset allocation weight determination method based on electric power big data and related equipment thereof Download PDF

Info

Publication number
CN112330022A
CN112330022A CN202011224130.5A CN202011224130A CN112330022A CN 112330022 A CN112330022 A CN 112330022A CN 202011224130 A CN202011224130 A CN 202011224130A CN 112330022 A CN112330022 A CN 112330022A
Authority
CN
China
Prior art keywords
asset
ith
model
prediction
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011224130.5A
Other languages
Chinese (zh)
Other versions
CN112330022B (en
Inventor
张兴华
陈绍真
汤克艰
张程
占少辉
常凯旋
俞果
廖会敏
王建文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Jiangxi Electric Power Co ltd
Guowang Xiongan Finance Technology Group Co ltd
State Grid Corp of China SGCC
Original Assignee
State Grid Jiangxi Electric Power Co ltd
Guowang Xiongan Finance Technology Group Co ltd
State Grid Corp of China SGCC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Jiangxi Electric Power Co ltd, Guowang Xiongan Finance Technology Group Co ltd, State Grid Corp of China SGCC filed Critical State Grid Jiangxi Electric Power Co ltd
Priority to CN202011224130.5A priority Critical patent/CN112330022B/en
Publication of CN112330022A publication Critical patent/CN112330022A/en
Application granted granted Critical
Publication of CN112330022B publication Critical patent/CN112330022B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses an asset allocation weight determination method based on electric big data and related equipment thereof, wherein the method comprises the following steps: after acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured, firstly inputting the reference income index data set into a pre-constructed income ratio prediction model to obtain a prediction income ratio set output by the income ratio prediction model; and determining an asset allocation weight set according to the prediction yield set. The method comprises the steps that a reference income index data set corresponding to an asset combination to be configured is input into an income prediction model, and then an accurate prediction income rate set output by the income prediction model can be obtained, so that an asset configuration weight set determined based on the accurate prediction income rate set is more accurate, and the effectiveness of the asset configuration weight is improved.

Description

Asset allocation weight determination method based on electric power big data and related equipment thereof
Technical Field
The application relates to the technical field of data processing, in particular to an asset configuration weight determination method based on electric power big data and related equipment thereof.
Background
According to the asset combination theory, it is known that, for an investor, before investing, the asset allocation weight of each asset to be allocated in the asset combination to be allocated needs to be determined, so that investment can be performed based on the asset allocation weight in the following.
However, how to accurately determine the asset allocation weight is an urgent technical problem to be solved.
Disclosure of Invention
In order to solve the technical problems in the prior art, the application provides an asset allocation weight determination method based on power big data and related equipment thereof, which can accurately determine asset allocation weights.
In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:
the embodiment of the application provides a method for determining asset configuration weight based on electric power big data, which comprises the following steps:
acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
determining an asset configuration weight set according to the prediction yield set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
Optionally, if the asset combination to be configured includes N assets to be configured, the profitability prediction model includes a profitability prediction sub-model corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is configured to predict a predicted profitability of the ith asset to be configured according to the reference profitability index data of the ith asset to be configured, where i is a positive integer, and i is not greater than N.
Optionally, the construction process of the yield prediction model is as follows:
acquiring historical income data of each asset to be configured;
training an ith preset model by using historical income data of an ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured; wherein i is a positive integer, and i is not more than N;
and obtaining the yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
Optionally, the training the ith preset model by using the historical revenue data of the ith asset to be configured to obtain the revenue rate prediction submodel corresponding to the ith asset to be configured includes:
generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured;
and training the ith preset model by using the training data of the ith asset to be configured to obtain a yield prediction sub-model corresponding to the ith asset to be configured.
Optionally, the training data includes model input data and model label data;
the training of the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model;
updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, returning to continue to execute the step of inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model and subsequent steps until a stop condition is reached, and determining the yield prediction sub-model corresponding to the ith asset to be configured according to the ith preset model.
Optionally, the method further includes:
acquiring a yield covariance matrix of the to-be-configured asset combination and an expected yield set corresponding to the to-be-configured asset combination; wherein the set of expected rates of return includes an expected rate of return for at least one asset to be deployed;
determining an asset allocation weight set according to the predicted profitability set, comprising:
and determining an asset allocation weight set according to the prediction yield set, the expected yield set and the yield covariance matrix of the asset combination to be allocated.
Optionally, the determining an asset allocation weight set according to the predicted profitability set, the expected profitability set and the profitability covariance matrix of the asset combination to be allocated includes:
generating a first constraint condition according to the prediction rate of return set and the expected rate of return set;
determining an objective function according to the yield covariance matrix of the asset combination to be configured;
and solving an asset configuration weight set according to the first constraint condition, a preset second constraint condition and the objective function.
The embodiment of the application also provides a device for determining asset configuration weight based on electric power big data, which comprises:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
the prediction unit is used for inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
the determining unit is used for determining an asset configuration weight set according to the prediction rate of return set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
An embodiment of the present application further provides an apparatus, where the apparatus includes a processor and a memory:
the memory is used for storing a computer program;
the processor is used for executing any implementation mode of the power big data asset configuration weight determination method provided by the embodiment of the application according to the computer program.
The embodiment of the present application further provides a computer-readable storage medium, which is used for storing a computer program, where the computer program is used for executing any implementation manner of the power big data based asset configuration weight determination method provided by the embodiment of the present application.
Compared with the prior art, the embodiment of the application has at least the following advantages:
according to the method for determining the asset allocation weight based on the electric big data, after an asset combination to be allocated and a reference income index data set corresponding to the asset combination to be allocated are obtained, the reference income index data set is input into a pre-constructed income ratio prediction model, and a prediction income ratio set output by the income ratio prediction model is obtained; and determining an asset allocation weight set according to the prediction yield set. The asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data of at least one asset to be configured; the set of predicted rates of return includes predicted rates of return for the at least one asset to be provisioned; the asset allocation weight set comprises asset allocation weights for at least one asset to be allocated.
Therefore, the prediction profitability of each asset to be configured can be accurately predicted by the aid of the profitability prediction model which is constructed in advance, so that an accurate prediction profitability set output by the profitability prediction model can be obtained after a reference profitability index data set corresponding to the asset combination to be configured is input into the profitability prediction model, an asset configuration weight set determined based on the accurate prediction profitability set is more accurate, and effectiveness of the asset configuration weight is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an asset allocation weight determination method based on electric big data according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an asset allocation weight determination device based on power big data according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an apparatus according to an embodiment of the present application.
Detailed Description
The inventor finds in research on asset allocation weights that, in a related technical scheme, for an asset combination to be allocated, on the premise of a risk neutral assumption, an arithmetic mean of historical profitability of each asset to be allocated can be determined as a predicted profitability of each asset to be allocated; and determining the asset allocation weight of each asset to be allocated based on the predicted profitability of each asset to be allocated. However, since the arithmetic mean of the historical profitability of an asset to be configured and the actual profitability of the asset to be configured in the future time period are different greatly, the predicted profitability determined based on the arithmetic mean of the historical profitability of the asset to be configured and the actual profitability of the asset to be configured in the future time period are different greatly, and therefore the asset configuration weight of the asset to be configured determined based on the predicted profitability of the asset to be configured is inaccurate.
In order to solve the technical problems of the background art and the defects of the related technical solutions, an embodiment of the present application provides a method for determining asset allocation weights based on power big data, and the method for determining asset allocation weights based on power big data includes: acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; inputting a reference income index data set corresponding to an asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; determining an asset configuration weight set according to the prediction yield set; the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data of at least one asset to be configured; the set of predicted rates of return includes predicted rates of return for the at least one asset to be provisioned; the asset allocation weight set comprises asset allocation weights for at least one asset to be allocated.
Therefore, the prediction profitability of each asset to be configured can be accurately predicted by the aid of the profitability prediction model which is constructed in advance, so that an accurate prediction profitability set output by the profitability prediction model can be obtained after a reference profitability index data set corresponding to the asset combination to be configured is input into the profitability prediction model, an asset configuration weight set determined based on the accurate prediction profitability set is more accurate, and effectiveness of the asset configuration weight is improved.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Method embodiment
Referring to fig. 1, the figure is a flowchart of an asset configuration weight determination method based on power big data according to an embodiment of the present application.
The asset configuration weight determining method based on the electric power big data comprises the following steps of S1-S4:
s1: and acquiring the asset combination to be configured.
The asset combination to be configured refers to the asset combination needing to be reasonably distributed with asset configuration weights; furthermore, the portfolio to be configured includes at least one asset to be configured. For example, a portfolio of assets to be configured may include N assets to be configured; n is a positive integer.
It should be noted that the portfolio to be configured is not limited in the embodiments of the present application, for example, the portfolio to be configured may be determined according to the assets to be configured selected by the investor. In addition, the embodiment of the application also does not limit the assets to be configured, for example, the assets to be configured can be securities and the like.
S2: and acquiring a reference income index data set corresponding to the asset combination to be configured.
The reference income index data set is used for recording reference income index data of each asset to be configured in the asset combination to be configured. It can be seen that, if the portfolio to be configured includes at least one asset to be configured, the reference revenue index data set may include reference revenue index data of the at least one asset to be configured. For example, if the portfolio to be configured includes N assets to be configured, the reference revenue index data set may include reference revenue index data of the 1 st asset to be configured through reference revenue index data of the nth asset to be configured.
In addition, the reference revenue index data is not limited in the embodiment of the present application, for example, in some cases, the reference revenue index data may be the latest historical revenue index data at the current time, and specifically includes: average market profit rate of the first four quarters, Average market sale rate of the first four quarters, Average net market rate of the first four quarters, Average market present rate of the first four quarters, Average industry prosperity Index value of the first four quarters, Average gross profit rate of the first four quarters, Average net profit-to-money ratio of the first four quarters, quarter profit rate of the first quarter, quarter end-of-quarter market profit rate of the first quarter, heterogeneous Moving Average line of the first quarter (MACD) Index value, Relative strong and weak Index of the first quarter (RSI) value, parallel line difference Index of the first quarter (DMA) value, VOL Index of the first quarter (also, success rate Index), electricity utilization Index of the first quarter, and electricity utilization amount of the first quarter.
It should be noted that, for a manufacturing enterprise using electric energy as a main production element, since the production and operation conditions of the enterprise can be reflected by the electric energy consumption of the enterprise to some extent, when the asset to be configured corresponds to the manufacturing enterprise using electric energy as a main production element, the reference income index data of the asset to be configured may include the amount of electricity used, the increase in the amount of electricity used, and the like.
S3: and inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model.
The profitability prediction model is used for predicting the prediction profitability of each asset to be configured in the asset combination to be configured.
The embodiment of the application does not limit the structure of the yield prediction model. In a possible implementation manner, if the asset combination to be configured includes N assets to be configured, the profitability prediction model may include a profitability prediction sub-model corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is configured to predict the predicted profitability of the ith asset to be configured according to the reference profitability index data of the ith asset to be configured, where i is a positive integer, and i is less than or equal to N.
That is, in some cases, the profitability prediction model may include a profitability prediction sub-model corresponding to the 1 st asset to be configured to a profitability prediction sub-model corresponding to the nth asset to be configured, so that the profitability prediction sub-model corresponding to the 1 st asset to be configured can predict the predicted profitability of the 1 st asset to be configured according to the reference profitability index data of the 1 st asset, the profitability prediction sub-model corresponding to the 2 nd asset to be configured can predict the predicted profitability of the 2 nd asset to be configured according to the reference profitability index data of the 2 nd asset to be configured, … … (and so on), and the profitability prediction sub-model corresponding to the nth asset to be configured can predict the predicted profitability of the nth asset to be configured according to the reference profitability index data of the nth asset to be configured.
The embodiment of the present application does not limit the process of constructing the yield prediction model, and for the convenience of understanding, the following description is made with reference to an example.
As an example, the process of constructing the profitability prediction model may specifically include steps 11 to 13:
step 11: and acquiring historical income data of each asset to be configured.
Wherein the historical benefit data is used to describe the historical benefit of the asset to be deployed. In addition, the embodiment of the present application does not limit the historical profit data. For example, the historical revenue data may include data used to calculate revenue indicator data over a preset historical period of time.
It should be noted that, the embodiment of the present application does not limit the obtaining manner of the historical profit data, for example, if the historical profit data includes data on finance (such as transaction price and financial data) and data on electric energy consumption (such as electric energy consumption and electric amount), the historical profit data may be obtained from a financial database and a national grid electric marketing database.
Step 12: and training the ith preset model by using the historical income data of the ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured. Wherein i is a positive integer, and i is not more than N.
To facilitate understanding of step 12, the following description is made with reference to an example.
As an example, step 12 may specifically include steps 121 to 122:
step 121: and generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured.
The training data of the ith asset to be configured is the training data required to be used for constructing the yield prediction submodel corresponding to the ith asset to be configured.
The embodiment of the present application does not limit the training data of the ith asset to be configured, for example, the training data of the ith asset to be configured may include model input data of the ith asset to be configured and model tag data of the ith asset to be configured. The model input data of the ith asset to be configured refers to data which needs to be input into the ith preset model in the training process of the ith preset model. The model label data of the ith asset to be configured refers to data required by correction of the ith preset model in the training process of the ith preset model.
It should be noted that the embodiment of the present application is not limited to the model input data of the ith asset to be configured, for example, the model input data of the ith asset to be configured may be historical revenue index data (e.g., at least one of an average market profit rate, an average market sale rate, an average market net rate, an average market present rate, an average industry scene degree index value, an average gross profit margin, an average net profit margin cash flow ratio, a quarterly revenue rate, an end-of-season market profit margin, a MACD index value, an RSI value, a DMA value, a VOL index, an electricity consumption amount, and an electricity consumption amount acceleration rate) of the ith asset to be configured within a preset historical time period. In addition, the embodiment of the present application also does not limit the model tag data of the ith asset to be configured, for example, the model tag data of the ith asset to be configured may be the profitability within the prediction time period corresponding to the preset historical time period. The prediction time period corresponding to the preset historical time period can be determined according to the preset historical time period, and the prediction time period corresponding to the preset historical time period is later than the preset historical time period.
It should be further noted that the historical revenue index data is similar to the above "reference revenue index data", and is not described herein again.
To facilitate understanding of the training data of the ith asset to be configured, the following description is made with reference to an example.
As an example, for the training data of the ith asset to be configured, when the model input data of the ith asset to be configured is the average market profit rate, the average market sale rate, the average net market rate, the average market present rate, the average industry prosperity index value, the average gross profit margin, the average net profit cash flow ratio in the first quarter of 2019 to 2020, and the quarter profit rate, the end-of-season market profit rate, the MACD index value, the RSI value, the DMA value, the VOL index, the electricity amount, and the electricity amount at the first quarter of 2020 are accelerated, the model tag data of the ith asset to be configured may be the quarter profit rate at the second quarter of 2020.
In some cases, because the data volume of the historical profit data is huge, in order to better extract the trend of the profit rate from the historical profit data, the historical profit data can be preprocessed according to a preprocessing means so as to generate training data based on the preprocessing result. Based on this, the embodiment of the present application further provides a possible implementation manner of step 121, which may specifically include steps 1211 to 1212:
step 1211: and preprocessing the historical income data of the ith asset to be configured to obtain the historical income index data of the ith asset to be configured.
The embodiment of the application is not limited to the preprocessing, for example, the preprocessing may include at least one of missing data value processing, data normalization processing, data regularization processing, data periodic summarization, yield calculation, MACD index value calculation, RSI value calculation, DMA value calculation, vol value calculation, power consumption amount (Elt) calculation, and power consumption amount acceleration EltM calculation.
In addition, the embodiment of the present application also does not limit the historical revenue index data of the ith asset to be configured, for example, the historical revenue index data of the ith asset to be configured may include historical revenue index data in a plurality of historical quarters.
Step 1212: and generating training data of the ith asset to be configured according to the historical income index data of the ith asset to be configured.
In the embodiment of the present application, after obtaining the historical income index data of the ith asset to be configured, the training data of the ith asset to be configured may be directly generated according to the historical income index data of the ith asset to be configured, and the generation process specifically may be: and determining income index data of the ith asset to be configured in the t-1 th historical quarter as model input data of the ith asset to be configured, and determining the seasonal income rate of the ith asset to be configured in the t-1 th historical quarter as model tag data of the ith asset to be configured. Wherein the t-1 th historical quarter is earlier than the t-th historical quarter.
Based on the related contents in the steps 1211 to 1212, after the historical profit data of the ith asset to be configured is obtained, preprocessing is performed on the historical profit data of the ith asset to be configured, and then training data of the ith asset to be configured is generated based on the preprocessing result, so that a profit rate prediction sub-model corresponding to the ith asset to be configured can be obtained based on the training data of the ith asset to be configured subsequently.
Step 122: and training the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction sub-model corresponding to the ith asset to be configured.
To facilitate understanding of step 122, the following description is made with reference to an example.
As an example, step 122 may specifically include steps 1221 to 1222:
step 1221: and inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model.
Wherein, the ith preset model is a preset model. In addition, the embodiment of the present application does not limit the ith preset model, for example, the ith preset model may be any machine learning model.
To facilitate understanding of the ith preset model, the following description is made with reference to an example.
As an example, the ith preset model may be represented by formula (1).
yi,t＝fi(Ai,Xi,t-1) (1)
In the formula, yi,tQuarterly profitability of the ith asset to be configured in the t historical quarterly; f. ofi() A prediction function used for the ith preset model; xi,t-1Revenue index data of the ith asset to be configured in the t-1 th historical quarter; a. theiA model parameter set for the ith preset model, and
Figure BDA0002763088570000101
m is the total number of model parameters of the ith preset model(ii) a i is a positive integer, i is not more than N, N is a positive integer, and N is the total number of assets to be configured; t is a positive integer, t is less than or equal to M, M is a positive integer, and M is the total number of historical quarters of the ith asset to be configured.
In the examples of the present application, X is not limitedi,t-1E.g. Xi,t-1＝[P/Et-4～t-1,P/St-4～t-1,P/Bt-4～t-1,P/CFt-4～t-1,PIt-4～t-1,GPt-4～t-1,NMt-4～t-1,I/CEt-4～t-1,Rt-1,P/Et-1,MACDt-1,RSIt-1,DMAt-1,volt-1,Eltt-1,EltMt-1]. Wherein, P/Et-4～t-1The average market profitability of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter; P/St-4～t-1The average market rate of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter is calculated; P/Bt-4～t-1The average net market rate of the ith asset to be configured in the t-4 th historical quarter to the t-1 st historical quarter is calculated; P/CFt-4～t-1The average market rate of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter is calculated; PI (proportional integral)t-4～t-1The average business prosperity index value of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter is obtained; GPt-4～t-1The average gross profit rate of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter; NMt-4～t-1The average net profit rate of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter; I/CEt-4～t-1The average net profit cash flow ratio of the ith asset to be configured in the t-4 th historical quarter to the t-1 th historical quarter; rt-1Quarterly profitability of the ith asset to be configured in the t-1 th historical quarter; P/Et-1The end-of-season market profitability of the ith asset to be configured in the t-1 th historical quarter; MACDt-1The MACD index value of the ith asset to be configured in the t-1 th historical quarter; RSIt-1The RSI value of the ith asset to be configured in the t-1 historical quarter is obtained; DMAt-1History at t-1 for ith asset to be configuredDMA values at quarterly; volt-1The VOL index of the ith asset to be configured in the t-1 th historical quarter is obtained; eltt-1The electricity consumption amount of the ith asset to be configured in the t-1 th historical quarter is calculated; EltMt-1The electricity consumption amount of the ith asset to be configured in the t-1 th historical season is increased.
Step 1222: determine whether a stop condition is met, if yes, go to step 1224; if not, execution 223 is performed.
It should be noted that the stopping condition is not limited in the embodiment of the present application, for example, the stopping condition may be that a difference between the model output data and the model tag data of the ith asset to be configured reaches a first threshold, that the update time of the ith preset model reaches a second threshold, and that a change rate of the difference between the model output data and the model tag data of the ith asset to be configured is lower than a third threshold.
Step 1223: and updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, and returning to continue to execute the steps 1221 to 1222.
Step 1224: and determining a yield prediction submodel corresponding to the ith asset to be configured according to the ith preset model.
Based on the related contents of the above steps 1221 to 1224, after the training data of the ith asset to be configured is obtained, the ith preset model is trained by using the training data of the ith asset to be configured, and according to the trained ith preset model, the yield prediction sub-model corresponding to the ith asset to be configured is determined (for example, the trained ith preset model is directly determined as the yield prediction sub-model corresponding to the ith asset to be configured), so that the yield prediction sub-model corresponding to the ith asset to be configured can achieve the prediction performance of the trained ith preset model.
Based on the related content of the above steps 121 to 122, after obtaining the historical profit data of the ith asset to be configured, the training data of the ith asset to be configured may be generated by using the historical profit data of the ith asset to be configured, and then the training data of the ith asset to be configured is used to train the ith preset model, so as to obtain the profit rate prediction sub-model corresponding to the ith asset to be configured, so that the profit rate prediction sub-model corresponding to the ith asset to be configured can accurately predict the profit rate of the ith asset to be configured in the future time period.
Step 13: and obtaining a yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
In the embodiment of the application, after acquiring the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured, the profitability prediction model can be generated according to the profitability prediction submodel corresponding to the 1 st asset to be configured to the profitability prediction submodel corresponding to the Nth asset to be configured (for example, the profitability prediction model is determined by directly combining the profitability prediction submodel corresponding to the 1 st asset to be configured to the profitability prediction submodel corresponding to the Nth asset to be configured), so that the yield prediction model comprises a yield prediction submodel corresponding to the 1 st asset to be configured to a yield prediction submodel corresponding to the Nth asset to be configured, therefore, the yield prediction model can predict the yield of each asset to be configured in the asset combination to be configured.
The set of predicted profitability comprises a predicted profitability of the at least one asset to be deployed. For example, if the asset combination to be configured includes N assets to be configured, the set of predicted profitability includes the predicted profitability of the 1 st asset to be configured to the predicted profitability of the nth asset to be configured.
Based on the related content of S2, after the reference income index data set corresponding to the asset combination to be configured is obtained, the reference income index data set corresponding to the asset combination to be configured may be directly input to the income ratio prediction model, so that the income ratio prediction model can predict and obtain the prediction income ratio set corresponding to the asset combination to be configured; the prediction process in the yield prediction model is as follows: if the yield prediction model comprises yield prediction sub-models corresponding to N assets to be configured, after the yield prediction model receives a reference yield index data set corresponding to an asset combination to be configured, the yield prediction sub-model corresponding to the 1 st asset to be configured predicts the yield prediction of the 1 st asset to be configured according to the reference yield index data of the 1 st asset to be configured, the yield prediction sub-model corresponding to the 2 nd asset to be configured predicts the yield prediction of the 2 nd asset to be configured according to the reference yield index data of the 2 nd asset to be configured, … … (analogy in turn), and the yield prediction sub-model corresponding to the Nth asset to be configured predicts the yield prediction of the Nth asset to be configured according to the reference yield index data of the Nth asset to be configured; and determining the set of the predicted profitability of the 1 st asset to be configured to the predicted profitability of the Nth asset to be configured as a set of the predicted profitability corresponding to the asset combination to be configured.
S4: and determining an asset configuration weight set according to the prediction yield set.
The asset configuration weight set is used for describing asset configuration weights of all assets to be configured in the asset combination to be configured; and the asset allocation weight set comprises asset allocation weights of at least one asset to be allocated. For example, if the asset combination to be configured includes N assets to be configured, the asset configuration weight set corresponding to the asset combination to be configured may include the asset configuration weight of the 1 st asset to be configured to the asset configuration weight of the nth asset to be configured.
In addition, the embodiment of the present application does not limit the method for determining the asset allocation weight set, and for convenience of understanding, the following description is made in conjunction with one possible embodiment.
In a possible embodiment, the process of determining the asset configuration weight set may specifically include steps 21 to 23:
step 21: and acquiring a yield covariance matrix of the asset combination to be configured.
The yield covariance matrix is used for recording the yield covariance between any two assets to be configured in the asset combination to be configured. In addition, the embodiments of the present application do not limit the yield covariance matrix, for example, the yield covariance matrix mayIs represented by
Figure BDA0002763088570000131
Wherein, the sigma is a yield covariance matrix of the asset combination to be configured; sigmaijThe method comprises the steps that the covariance between the yield rate of the ith asset to be configured and the yield rate of the jth asset to be configured is obtained, i is a positive integer, i is less than or equal to N, j is a positive integer, j is less than or equal to N, and i is not equal to j; sigmaiiThe yield variance of the ith asset to be configured.
It should be noted that, in the embodiments of the present application, the method for obtaining the yield covariance matrix is not limited, and any method capable of obtaining the yield covariance matrix may be used for implementation. For example, step 21 may specifically be: and generating a yield covariance matrix of the asset combination to be configured according to the quarterly yield of the 1 st asset to be configured in the historical quarterly nearest to the current time to the quarterly yield of the Nth asset to be configured in the historical quarterly nearest to the current time.
Step 22: and acquiring an expected profitability set corresponding to the asset combination to be configured.
The system comprises an investment pool, an expected profitability set and a resource allocation set, wherein the expected profitability set is used for recording an expected value set by an investor for each asset to be configured in the asset combination to be configured; moreover, the set of expected rates of return includes an expected rate of return for the at least one asset to be deployed. For example, if the portfolio to be configured includes N assets to be configured, the expected profitability set corresponding to the portfolio to be configured may include the expected profitability of the 1 st asset to be configured to the expected profitability of the nth asset to be configured.
It should be noted that the embodiment of the present application does not limit the manner of obtaining the expected profitability set, for example, the expected profitability set may be preset by the investor.
Step 23: and determining an asset allocation weight set according to the prediction yield set, the expected yield set and the yield covariance matrix of the asset combination to be allocated.
The embodiment of the present application does not limit the determination process of the asset configuration weight set, and for the convenience of understanding, the following description is made with reference to an example.
As an example, the process of determining the asset configuration weight set may specifically include steps 231-233:
step 231: and generating a first constraint condition according to the prediction yield set and the expected yield set.
It should be noted that the first constraint is not limited in the embodiment of the present application, and for example, the first constraint may be expressed as formula (2).
Rp＝W·RF (2)
In the formula, RpIs a set of expected profitability; rFIs a set of predicted profitability; w configures a set of weights for the asset.
Step 232: and determining an objective function according to the yield covariance matrix of the asset combination to be configured.
It should be noted that the present embodiment does not limit the objective function, and for example, the objective function may be expressed as formula (3).
minσ2＝W·∑·WT (3)
In the formula, σ2The loss value of the asset combination to be configured is obtained; w is an asset configuration weight set; the sigma is a yield covariance matrix of the asset combination to be configured; min σ2Means that the loss value of the portfolio to be configured is minimized.
Step 233: and solving the asset configuration weight set according to the first constraint condition, the preset second constraint condition and the objective function.
The second constraint condition may be preset, and the embodiment of the present application does not limit the second constraint condition. For example, the second constraint may include formula (4) and formula (5).
Z·W＝1 (4)
Figure BDA0002763088570000141
Wherein Z is an Nx 1-dimensional column vector, and Z is [1,1, …,1 ═ b](ii) a W is an asset configuration weight set; w is aiAnd configuring the weight for the asset of the ith asset to be configured.
As can be seen from the above equations (4) and (5), if the portfolio of assets to be configured includes N assets to be configured, the second constraint condition may include that the sum of the asset configuration weights of the N assets to be configured is equal to 1 (i.e.,
Figure BDA0002763088570000142
and the asset allocation weight of each asset to be allocated is non-negative.
Based on the related contents of the above steps 231 to 233, in the embodiment of the present application, when the yield covariance matrices of the prediction yield set, the expected yield set, and the to-be-configured asset combination are obtained, an objective function, a first constraint condition, and a second constraint condition may be obtained according to the yield covariance matrices of the prediction yield set, the expected yield set, and the to-be-configured asset combination; and solving the asset configuration weight set based on the objective function, the first constraint condition, the second constraint condition and a preset third constraint condition.
Based on the related contents from S1 to S3, in the method for determining asset allocation weights based on big data of electric power provided in the embodiment of the present application, after acquiring an asset combination to be allocated and a reference revenue index data set corresponding to the asset combination to be allocated, first inputting the reference revenue index data set to a pre-constructed revenue rate prediction model, and obtaining a prediction revenue rate set output by the revenue rate prediction model; and determining an asset allocation weight set according to the prediction yield set. The asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data of at least one asset to be configured; the set of predicted rates of return includes predicted rates of return for the at least one asset to be provisioned; the asset allocation weight set comprises asset allocation weights for at least one asset to be allocated.
Therefore, the prediction profitability of each asset to be configured can be accurately predicted by the aid of the profitability prediction model which is constructed in advance, so that an accurate prediction profitability set output by the profitability prediction model can be obtained after a reference profitability index data set corresponding to the asset combination to be configured is input into the profitability prediction model, an asset configuration weight set determined based on the accurate prediction profitability set is more accurate, and effectiveness of the asset configuration weight is improved.
Based on the method for determining the asset configuration weight based on the big data of the power provided by the embodiment of the method, the embodiment of the application also provides a device for determining the asset configuration weight based on the big data of the power, which is explained and explained with reference to the attached drawings.
Device embodiment
Please refer to the above method embodiment for technical details of the power big data asset configuration weight-based determination device provided by the device embodiment.
Referring to fig. 2, the figure is a schematic diagram of an asset allocation weight determination device based on power big data according to an embodiment of the present application.
The device 200 for determining asset configuration weight based on big electric power data provided by the embodiment of the application comprises:
a first obtaining unit 201, configured to obtain an asset combination to be configured and a reference revenue index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
the prediction unit 202 is configured to input the reference revenue index data set corresponding to the asset combination to be configured into a pre-constructed revenue rate prediction model, so as to obtain a prediction revenue rate set output by the revenue rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
a determining unit 203, configured to determine an asset configuration weight set according to the predicted profitability set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
In a possible implementation manner, if the asset combination to be configured includes N assets to be configured, the profitability prediction model includes profitability prediction sub-models corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is used for predicting the predicted profitability of the ith asset to be configured according to the reference profitability index data of the ith asset to be configured, where i is a positive integer, and i is less than or equal to N.
In a possible implementation, the construction process of the yield prediction model is as follows:
acquiring historical income data of each asset to be configured;
training an ith preset model by using historical income data of an ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured; wherein i is a positive integer, and i is not more than N;
and obtaining the yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
In a possible implementation manner, the training of the ith preset model by using historical revenue data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured;
and training the ith preset model by using the training data of the ith asset to be configured to obtain a yield prediction sub-model corresponding to the ith asset to be configured.
In one possible embodiment, the training data includes model input data and model label data;
the training of the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model;
updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, returning to continue to execute the step of inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model and subsequent steps until a stop condition is reached, and determining the yield prediction sub-model corresponding to the ith asset to be configured according to the ith preset model.
In a possible implementation, the device 200 for determining a weight based on power big data asset allocation further includes:
the second acquisition unit is used for acquiring the yield covariance matrix of the asset combination to be configured and the expected yield set corresponding to the asset combination to be configured; wherein the set of expected rates of return includes an expected rate of return for at least one asset to be deployed;
the determining unit 203 is specifically configured to determine an asset allocation weight set according to the predicted profitability set, the expected profitability set, and a profitability covariance matrix of the asset combination to be allocated.
In a possible implementation manner, the determining unit 203 is specifically configured to:
generating a first constraint condition according to the prediction rate of return set and the expected rate of return set;
determining an objective function according to the yield covariance matrix of the asset combination to be configured;
and solving an asset configuration weight set according to the first constraint condition, a preset second constraint condition and the objective function.
Based on the related content of the device 200 for determining the asset allocation weight based on the big data, for the device 200 for determining the asset allocation weight based on the big data, after acquiring the asset combination to be allocated and the reference income index data set corresponding to the asset combination to be allocated, firstly inputting the reference income index data set into a pre-constructed income rate prediction model, and obtaining a prediction income rate set output by the income rate prediction model; and determining an asset allocation weight set according to the prediction yield set. The asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data of at least one asset to be configured; the set of predicted rates of return includes predicted rates of return for the at least one asset to be provisioned; the asset allocation weight set comprises asset allocation weights for at least one asset to be allocated.
Therefore, the prediction profitability of each asset to be configured can be accurately predicted by the aid of the profitability prediction model which is constructed in advance, so that an accurate prediction profitability set output by the profitability prediction model can be obtained after a reference profitability index data set corresponding to the asset combination to be configured is input into the profitability prediction model, an asset configuration weight set determined based on the accurate prediction profitability set is more accurate, and effectiveness of the asset configuration weight is improved.
Based on the method for determining asset configuration weight based on electric big data provided by the above method embodiment, the embodiment of the present application further provides a device, which is explained and explained below with reference to the accompanying drawings.
Apparatus embodiment
Please refer to the above method embodiment for the device technical details provided by the device embodiment.
Referring to fig. 3, the drawing is a schematic structural diagram of an apparatus provided in the embodiment of the present application.
The device 300 provided by the embodiment of the application comprises: a processor 301 and a memory 302;
the memory 302 is used for storing computer programs;
the processor 301 is configured to execute any implementation of the method for determining the asset allocation weight based on the power big data according to the above method embodiments. That is, the processor 301 is configured to perform the following steps:
acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
determining an asset configuration weight set according to the prediction yield set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
Optionally, if the asset combination to be configured includes N assets to be configured, the profitability prediction model includes a profitability prediction sub-model corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is configured to predict a predicted profitability of the ith asset to be configured according to the reference profitability index data of the ith asset to be configured, where i is a positive integer, and i is not greater than N.
Optionally, the construction process of the yield prediction model is as follows:
acquiring historical income data of each asset to be configured;
training an ith preset model by using historical income data of an ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured; wherein i is a positive integer, and i is not more than N;
and obtaining the yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
Optionally, the training the ith preset model by using the historical revenue data of the ith asset to be configured to obtain the revenue rate prediction submodel corresponding to the ith asset to be configured includes:
generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured;
and training the ith preset model by using the training data of the ith asset to be configured to obtain a yield prediction sub-model corresponding to the ith asset to be configured.
Optionally, the training data includes model input data and model label data;
the training of the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model;
updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, returning to continue to execute the step of inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model and subsequent steps until a stop condition is reached, and determining the yield prediction sub-model corresponding to the ith asset to be configured according to the ith preset model.
Optionally, the method further includes:
acquiring a yield covariance matrix of the to-be-configured asset combination and an expected yield set corresponding to the to-be-configured asset combination; wherein the set of expected rates of return includes an expected rate of return for at least one asset to be deployed;
determining an asset allocation weight set according to the predicted profitability set, comprising:
and determining an asset allocation weight set according to the prediction yield set, the expected yield set and the yield covariance matrix of the asset combination to be allocated.
Optionally, the determining an asset allocation weight set according to the predicted profitability set, the expected profitability set and the profitability covariance matrix of the asset combination to be allocated includes:
generating a first constraint condition according to the prediction rate of return set and the expected rate of return set;
determining an objective function according to the yield covariance matrix of the asset combination to be configured;
and solving an asset configuration weight set according to the first constraint condition, a preset second constraint condition and the objective function.
The above is related to the apparatus 300 provided in the embodiments of the present application.
Based on the method for determining asset configuration weight based on power big data provided by the method embodiment, the embodiment of the application further provides a computer readable storage medium.
Media embodiments
Media embodiments provide technical details of computer-readable storage media, please refer to method embodiments.
The embodiment of the application provides a computer-readable storage medium for storing a computer program, wherein the computer program is used for executing any implementation mode of the power big data asset configuration weight determination method provided by the method embodiment. That is, the computer program is for performing the steps of:
acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
determining an asset configuration weight set according to the prediction yield set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
Optionally, if the asset combination to be configured includes N assets to be configured, the profitability prediction model includes a profitability prediction sub-model corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is configured to predict a predicted profitability of the ith asset to be configured according to the reference profitability index data of the ith asset to be configured, where i is a positive integer, and i is not greater than N.
Optionally, the construction process of the yield prediction model is as follows:
acquiring historical income data of each asset to be configured;
training an ith preset model by using historical income data of an ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured; wherein i is a positive integer, and i is not more than N;
and obtaining the yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
Optionally, the training the ith preset model by using the historical revenue data of the ith asset to be configured to obtain the revenue rate prediction submodel corresponding to the ith asset to be configured includes:
generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured;
and training the ith preset model by using the training data of the ith asset to be configured to obtain a yield prediction sub-model corresponding to the ith asset to be configured.
Optionally, the training data includes model input data and model label data;
the training of the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model;
updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, returning to continue to execute the step of inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model and subsequent steps until a stop condition is reached, and determining the yield prediction sub-model corresponding to the ith asset to be configured according to the ith preset model.
Optionally, the method further includes:
acquiring a yield covariance matrix of the to-be-configured asset combination and an expected yield set corresponding to the to-be-configured asset combination; wherein the set of expected rates of return includes an expected rate of return for at least one asset to be deployed;
determining an asset allocation weight set according to the predicted profitability set, comprising:
and determining an asset allocation weight set according to the prediction yield set, the expected yield set and the yield covariance matrix of the asset combination to be allocated.
Optionally, the determining an asset allocation weight set according to the predicted profitability set, the expected profitability set and the profitability covariance matrix of the asset combination to be allocated includes:
generating a first constraint condition according to the prediction rate of return set and the expected rate of return set;
determining an objective function according to the yield covariance matrix of the asset combination to be configured;
and solving an asset configuration weight set according to the first constraint condition, a preset second constraint condition and the objective function.
The above is related to the computer-readable storage medium provided in the embodiments of the present application.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.

Claims (10)

1. A method for determining asset allocation weight based on electric power big data is characterized by comprising the following steps:
acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
determining an asset configuration weight set according to the prediction yield set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
2. The method of claim 1, wherein if the asset combination to be configured includes N assets to be configured, the profitability prediction model includes profitability prediction sub-models corresponding to the N assets to be configured, and the profitability prediction sub-model corresponding to the ith asset to be configured is configured to predict a predicted profitability of the ith asset to be configured according to reference profitability index data of the ith asset to be configured, i is a positive integer, and i is less than or equal to N.
3. The method of claim 2, wherein the profitability prediction model is constructed by:
acquiring historical income data of each asset to be configured;
training an ith preset model by using historical income data of an ith asset to be configured to obtain an income rate prediction sub-model corresponding to the ith asset to be configured; wherein i is a positive integer, and i is not more than N;
and obtaining the yield prediction model according to the yield prediction submodel corresponding to the 1 st asset to be configured to the yield prediction submodel corresponding to the Nth asset to be configured.
4. The method according to claim 3, wherein the training of the ith preset model by using the historical revenue data of the ith asset to be configured to obtain the revenue rate prediction submodel corresponding to the ith asset to be configured comprises:
generating training data of the ith asset to be configured according to the historical income data of the ith asset to be configured;
and training the ith preset model by using the training data of the ith asset to be configured to obtain a yield prediction sub-model corresponding to the ith asset to be configured.
5. The method of claim 4, wherein the training data comprises model input data and model label data;
the training of the ith preset model by using the training data of the ith asset to be configured to obtain the yield prediction submodel corresponding to the ith asset to be configured includes:
inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model;
updating the ith preset model according to the model output data and the model tag data of the ith asset to be configured, returning to continue to execute the step of inputting the model input data of the ith asset to be configured into the ith preset model to obtain the model output data output by the ith preset model and subsequent steps until a stop condition is reached, and determining the yield prediction sub-model corresponding to the ith asset to be configured according to the ith preset model.
6. The method of claim 1, further comprising:
acquiring a yield covariance matrix of the to-be-configured asset combination and an expected yield set corresponding to the to-be-configured asset combination; wherein the set of expected rates of return includes an expected rate of return for at least one asset to be deployed;
determining an asset allocation weight set according to the predicted profitability set, comprising:
and determining an asset allocation weight set according to the prediction yield set, the expected yield set and the yield covariance matrix of the asset combination to be allocated.
7. The method of claim 6, wherein determining a set of asset allocation weights based on the set of predicted rates of return, the set of expected rates of return, and a rate of return covariance matrix for the portfolio of assets to be allocated comprises:
generating a first constraint condition according to the prediction rate of return set and the expected rate of return set;
determining an objective function according to the yield covariance matrix of the asset combination to be configured;
and solving an asset configuration weight set according to the first constraint condition, a preset second constraint condition and the objective function.
8. An apparatus for determining a weight based on power big data asset allocation, the apparatus comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring an asset combination to be configured and a reference income index data set corresponding to the asset combination to be configured; wherein the asset combination to be configured comprises at least one asset to be configured; the reference revenue index data set comprises reference revenue index data for at least one asset to be configured;
the prediction unit is used for inputting the reference income index data set corresponding to the asset combination to be configured into a pre-constructed income rate prediction model to obtain a prediction income rate set output by the income rate prediction model; wherein the set of predicted rates of return includes a predicted rate of return for at least one asset to be provisioned;
the determining unit is used for determining an asset configuration weight set according to the prediction rate of return set; wherein the asset configuration weight set comprises asset configuration weights of at least one asset to be configured.
9. An apparatus, comprising a processor and a memory:
the memory is used for storing a computer program;
the processor is configured to perform the method of any one of claims 1-7 in accordance with the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program for performing the method of any of claims 1-7.
CN202011224130.5A 2020-11-05 2020-11-05 Power big data asset configuration weight determination method and related equipment thereof Active CN112330022B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011224130.5A CN112330022B (en) 2020-11-05 2020-11-05 Power big data asset configuration weight determination method and related equipment thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011224130.5A CN112330022B (en) 2020-11-05 2020-11-05 Power big data asset configuration weight determination method and related equipment thereof

Publications (2)

Publication Number Publication Date
CN112330022A true CN112330022A (en) 2021-02-05
CN112330022B CN112330022B (en) 2023-10-10

Family

ID=74315960

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011224130.5A Active CN112330022B (en) 2020-11-05 2020-11-05 Power big data asset configuration weight determination method and related equipment thereof

Country Status (1)

Country Link
CN (1) CN112330022B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446984A (en) * 2018-03-20 2018-08-24 张家林 A kind of investment data management method and device
CN108717664A (en) * 2018-04-03 2018-10-30 平安科技（深圳）有限公司 Portfolio Optimization method, apparatus and storage medium
CN109993428A (en) * 2019-03-28 2019-07-09 第四范式（北京）技术有限公司 Resource allocation methods and device
KR20190143543A (en) * 2018-06-14 2019-12-31 (주)밸류파인더스 Methode for Performance Improvement of Portfolio Asset Allocation Using Recurrent Reinforcement Learning
CN111340632A (en) * 2020-03-03 2020-06-26 支付宝(杭州)信息技术有限公司 Resource control method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446984A (en) * 2018-03-20 2018-08-24 张家林 A kind of investment data management method and device
CN108717664A (en) * 2018-04-03 2018-10-30 平安科技（深圳）有限公司 Portfolio Optimization method, apparatus and storage medium
KR20190143543A (en) * 2018-06-14 2019-12-31 (주)밸류파인더스 Methode for Performance Improvement of Portfolio Asset Allocation Using Recurrent Reinforcement Learning
CN109993428A (en) * 2019-03-28 2019-07-09 第四范式（北京）技术有限公司 Resource allocation methods and device
CN111340632A (en) * 2020-03-03 2020-06-26 支付宝(杭州)信息技术有限公司 Resource control method and device

Also Published As

Publication number Publication date
CN112330022B (en) 2023-10-10

Similar Documents

Publication Publication Date Title
CA3092306C (en) Method and system of dynamic model selection for time series forecasting
Li et al. Risk prediction in financial management of listed companies based on optimized BP neural network under digital economy
WO2019001120A1 (en) Method and system for processing dynamic pricing data of commodity
CN110400021B (en) Bank branch cash usage prediction method and device
US8577791B2 (en) System and computer program for modeling and pricing loan products
Khedmati et al. An online portfolio selection algorithm using clustering approaches and considering transaction costs
Xu et al. A large CVaR-based portfolio selection model with weight constraints
WO2019214455A1 (en) Data sequence prediction method and computing apparatus
Somers et al. Quantile regression for modelling distributions of profit and loss
CN105719013A (en) Method and system for calculating enterprise asset debts
Chen et al. A study on operational risk and credit portfolio risk estimation using data analytics
Ozcalici et al. Optimizing filter rule parameters with genetic algorithm and stock selection with artificial neural networks for an improved trading: The case of Borsa Istanbul
Li et al. Financial risk prediction for listed companies using IPSO-BP neural network
JP2018503927A (en) Segmentation and stratification of composite portfolio of investment securities
CN111667307B (en) Method and device for predicting financial product sales volume
CN104321800A (en) Price target builder
US20090063328A1 (en) Systems and Methods for Consumer Mortgage Debt Decision Support
CN112766814A (en) Training method, device and equipment for credit risk pressure test model
CN112330022A (en) Asset allocation weight determination method based on electric power big data and related equipment thereof
CN114742657A (en) Investment target planning method and system
Fu et al. Binary tree pricing method of farmland management right mortgage based on machine learning and complex network algorithm
Gao et al. Big data analysis with momentum strategy on data-driven trading
Sen et al. Optimum risk portfolio and eigen portfolio: a comparative analysis using selected stocks from the Indian stock market
Farouq et al. Real exchange rate and economic growth: The interacting role of financial development in Nigeria
CN113421014A (en) Target enterprise determination method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant