CN116485537A - Financial product selection method, device, processor and electronic equipment - Google Patents

Financial product selection method, device, processor and electronic equipment Download PDF

Info

Publication number
CN116485537A
CN116485537A CN202310450124.9A CN202310450124A CN116485537A CN 116485537 A CN116485537 A CN 116485537A CN 202310450124 A CN202310450124 A CN 202310450124A CN 116485537 A CN116485537 A CN 116485537A
Authority
CN
China
Prior art keywords
financial
data
target
products
financial products
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.)
Pending
Application number
CN202310450124.9A
Other languages
Chinese (zh)
Inventor
伏勇
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.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
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 Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202310450124.9A priority Critical patent/CN116485537A/en
Publication of CN116485537A publication Critical patent/CN116485537A/en
Pending legal-status Critical Current

Links

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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Evolutionary Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Technology Law (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a financial product selection method, a financial product selection device, a financial product selection processor and electronic equipment. Relates to the field of financial science and technology, and the method comprises the following steps: acquiring M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data; inputting target financial data into N prediction models respectively, and outputting N groups of profit results, wherein each group of profit results comprises the profit results of M candidate financial products; for each group of income results, sorting the associated M candidate financial products according to the income results to obtain N sorting results; judging whether each financial product meets the preset requirement according to the N sorting results, and determining the financial product combination according to the financial products meeting the preset requirement. By the method and the device, the problem that the financial product combination is difficult to meet the requirements of users when the financial product combination is determined by using single specific data in the related technology is solved.

Description

Financial product selection method, device, processor and electronic equipment
Technical Field
The present application relates to the field of financial science and technology, and in particular, to a method and apparatus for selecting a financial product, a processor, and an electronic device.
Background
With the development of artificial intelligence, more and more researchers use the artificial intelligence as an analysis tool of financial products, predict the conditions of different financial products through machine learning, and recommend financial products meeting the requirements for customers.
The conventional technique trains a linear model using a specific data set, so that the trained linear model predicts a financial product. However, the linear model in the technology can only make predictions on a financial product by using one feature, and the linear model cannot identify the existence mode and the dynamics of the whole stock market because the factors affecting the stock market are not dependent on a single factor but are jointly determined by a plurality of factors such as news, economic conditions and the like.
Aiming at the problem that the financial product combination is difficult to meet the requirements of users when the financial product combination is determined by utilizing single specific data in the related art, no effective solution is proposed at present.
Disclosure of Invention
The main objective of the present application is to provide a method, an apparatus, a processor and an electronic device for selecting a financial product, so as to solve the problem that the financial product combination is difficult to satisfy the requirement of a user when determining the financial product combination by using single specific data in the related art.
In order to achieve the above object, according to one aspect of the present application, there is provided a method of selecting a financial product. The method comprises the following steps: acquiring M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data; inputting target financial data into N prediction models respectively, and outputting N groups of profit results, wherein each group of profit results comprises the profit results of M candidate financial products; for each group of income results, sorting the associated M candidate financial products according to the income results to obtain N sorting results; judging whether each financial product meets a preset requirement according to N sorting results, and determining a financial product combination according to the financial products meeting the preset requirement, wherein the preset requirement refers to a sequence of the financial products in the preset proportion before each sorting result, the financial product combination comprises Z target financial products, Z is smaller than M, and M, N, Z is a positive integer.
Optionally, obtaining M candidate financial products in the target time period, and processing financial data associated with the M candidate financial products, where obtaining the target financial data includes: acquiring M candidate financial products and financial reports of the M candidate financial products from a financial consultation website, and acquiring financial data of the financial products from the financial reports to obtain M financial data; preprocessing M financial data to M processed financial data, wherein the preprocessing mode at least comprises one of the following steps: standardized processing and filling of missing values; and for each processed financial data, respectively arranging the importance degrees of all the included financial feature data to obtain M financial feature data sequences, selecting the financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as target financial data.
Optionally, for each processed financial data, ranking the importance degrees of all the financial feature data included, to obtain M financial feature data sequences includes: respectively inputting the M processed financial data into a sequencing model to obtain the weight value of each financial characteristic data of each processed financial data; descending order arrangement is carried out on the financial characteristic data in each processed financial data according to the magnitude relation of the weight values, so that M financial characteristic data sequences are obtained; selecting financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as target financial data comprises: and selecting a first preset number of feature data from each financial feature data sequence respectively, and combining the selected financial feature data into target financial data.
Optionally, the N prediction models include N-1 sub-prediction models and an aggregate model aggregated from the N-1 sub-prediction models, the prediction models being trained by: acquiring Y historical financial products, and processing financial data associated with the Y historical financial products to obtain Y sample data; using Y sample data as a training set, and training N-1 preset sub-prediction models by using the training set to obtain N-1 sub-prediction models; performing aggregation operation on the N-1 sub-prediction models by using an aggregation algorithm to obtain an initial aggregation model; and training an initial aggregation model by using Y sample data to obtain an aggregation model, and determining the aggregation model and the N-1 sub-prediction models as N prediction models under the condition that the aggregation model meets the reference model requirement, wherein the condition that the aggregation model meets the reference model requirement means that the parameters of the aggregation model meet the parameter requirement of the reference model.
Optionally, determining the financial product combination from the financial products meeting the preset requirements includes: screening target financial products from financial products meeting preset requirements according to the relative income to obtain Z target financial products; the Z target financial product combinations are financial product combinations.
Optionally, selecting target financial products from the financial products meeting the preset requirement according to the relative yields, and obtaining Z target financial products includes: inputting target financial data of financial products meeting preset requirements into a sequencing model to obtain weight values of various financial characteristic data of each financial product in a target time period, and calculating the percentage of the weight value of each financial characteristic data to the total weight value; and calculating the fluctuation rate of each financial product in the target time period by using the percentage, and determining the financial product as the target financial product under the condition that the fluctuation rate is smaller than the fluctuation threshold value to obtain Z target financial products.
Optionally, the Z target financial product combinations are financial product combinations comprising: calculating the return rate of return according to the return result of each target financial product to obtain Z return rates of return, and calculating the summer ratio by using the Z return rates of return; judging whether the summer ratio is larger than a preset summer ratio threshold value or not; and under the condition that the summer ratio is smaller than or equal to a preset summer ratio threshold, re-determining Z target financial products from financial products meeting preset requirements in a target time period, and combining the re-determined Z target financial products into a financial product combination, wherein the summer ratio of the re-determined Z target financial products is larger than the preset summer ratio threshold.
In order to achieve the above object, according to another aspect of the present application, there is provided a selecting device for a financial product. The device comprises: the acquisition unit is used for acquiring M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data; the input unit is used for respectively inputting the target financial data into the N prediction models and outputting N groups of income results, wherein each group of income results comprise income results of M candidate financial products; the ordering unit is used for ordering the associated M candidate financial products according to the profit results to obtain N ordering results; the judging unit is used for judging whether each financial product meets the preset requirement according to the N sorting results, and determining a financial product combination according to the financial products meeting the preset requirement, wherein the preset requirement refers to a sequence of the financial products in a preset proportion before each sorting result, the financial product combination comprises Z target financial products, Z is smaller than M, and M, N, Z is a positive integer.
According to another aspect of the embodiment of the present invention, there is further provided a processor, configured to execute a program, where the program, when executed, controls a device in which a nonvolatile storage medium is located to execute a method for selecting a financial product.
According to another aspect of embodiments of the present invention, there is also provided an electronic device including one or more processors and a memory; the memory has stored therein computer readable instructions for execution by the processor, wherein the computer readable instructions when executed perform a method of selecting a financial product.
Through the application, the following steps are adopted: acquiring M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data; inputting target financial data into N prediction models respectively, and outputting N groups of profit results, wherein each group of profit results comprises the profit results of M candidate financial products; for each group of income results, sorting the associated M candidate financial products according to the income results to obtain N sorting results; judging whether each financial product meets preset requirements according to N sorting results, and determining a financial product combination according to the financial products meeting the preset requirements, wherein the preset requirements refer to a sequence of the financial products in a preset proportion before each sorting result, Z target financial products are contained in the financial product combination, Z is smaller than M and M, N, Z is a positive integer, the problem that the financial product combination is difficult to meet the requirements of users when the financial product combination is determined by single specific data in the related art is solved, the characteristics are input into the model by acquiring a plurality of characteristics in the financial products, a profit result is obtained, and the target financial product combination is determined by utilizing the profit result, so that the effect of recommending the financial product combination required by the users is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a method of selecting a financial product provided in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram of financial feature data weights provided in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram of a selection device for a financial product provided in accordance with an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party.
The present invention will be described with reference to preferred embodiments, and FIG. 1 is a flowchart of a method for selecting a financial product according to an embodiment of the present application, as shown in FIG. 1, comprising the steps of:
Step S101, M candidate financial products are obtained in a target time period, and financial data associated with the M candidate financial products are processed to obtain target financial data.
In order to obtain a high-performance and high-stability financial product combination in a target time period, a plurality of candidate financial products in the target time period need to be obtained, and the candidate financial products are evaluated to obtain the target financial product combination.
Specifically, the financial products may be investment products including stocks, futures, gold, foreign exchange, funds, etc. containing a certain risk and income, the income is brought to the customer by the price change of the products, and the target time period may be in a time period unit of quarter or year, for example, a plurality of stocks in one quarter are obtained as candidate financial products. In the case that the candidate financial products are stocks, the financial data associated with the candidate financial products may refer to financial data extracted from quarter financial reports and macro financial reports of each stock, the financial data is processed and the financial feature data is selected, and the selected financial feature data is used as target financial data to be input into the prediction model.
Step S102, inputting the target financial data into N prediction models respectively, and outputting N groups of income results, wherein each group of income results comprises income results of M candidate financial products.
Specifically, the prediction model refers to a stock gain prediction model obtained based on a machine learning algorithm, and can comprise a feedforward neural network model, a random forest model, a self-adaptive neural fuzzy reasoning system and an aggregation model obtained by aggregation of a plurality of machine learning models, wherein the feedforward neural network model can measure the stability of a financial product; the random forest is a classifier for training and predicting samples by using trees, namely, the random forest can be used for predicting and classifying the benefits of financial products; the self-adaptive neural fuzzy inference system is a novel fuzzy inference system structure which organically combines fuzzy logic and a neural network, and can obtain the income inference result of financial products by utilizing the inference system. The target financial data corresponding to each stock is input into a plurality of prediction models, the relative income data of each stock is output and obtained, and the income situation of the financial product is inferred and predicted by utilizing the plurality of prediction models, so that errors obtained by a single model can be eliminated, and further, a relatively accurate financial product combination result is obtained.
Step S103, for each group of profit results, sorting the associated M candidate financial products according to the profit results to obtain N sorting results.
Specifically, each set of profit results includes relative profit data of each candidate stock, and the financial products corresponding to each relative profit data are ordered in reverse order according to the value of the relative profit data to obtain a set of ordering results, further, the profit results obtained according to each prediction model are all ordered in reverse order to obtain a plurality of ordering results, for example, 60 stocks need to be input into 4 prediction models in total in the current time period, when the target financial data is input into the prediction models, 4 sets of profit results can be obtained, and the ordering sequence in each set of profit results is obtained by ordering in reverse order according to the profit results of 60 stocks.
Step S104, judging whether each financial product meets a preset requirement according to N sorting results, and determining a financial product combination according to the financial products meeting the preset requirement, wherein the preset requirement is a sequence of the financial products in a preset proportion before each sorting result, the financial product combination comprises Z target financial products, Z is smaller than M, and M, N, Z is a positive integer.
Specifically, the preset requirement may mean that the financial product needs to be located in the first third of each ranking order, for example, 60 candidate stocks are obtained in total, each stock is input into four prediction models, four sets of profit results are output by the models, and descending ranking is performed according to the profit results of 60 stocks, so as to obtain 4 ranking results. Further, the stocks in the first third of the arrangement results are obtained, whether the arrangement orders of the obtained stocks are all in the first third of the arrangement results of the remaining three groups is judged, and if the stocks are all in the first third of the arrangement results, the stocks are added into the financial product combination.
According to the financial product selection method, M candidate financial products are obtained in a target time period, and financial data associated with the M candidate financial products are processed to obtain target financial data; inputting target financial data into N prediction models respectively, and outputting N groups of profit results, wherein each group of profit results comprises the profit results of M candidate financial products; for each group of income results, sorting the associated M candidate financial products according to the income results to obtain N sorting results; judging whether each financial product meets preset requirements according to N sorting results, and determining a financial product combination according to the financial products meeting the preset requirements, wherein the preset requirements refer to a sequence of the financial products in a preset proportion before each sorting result, Z is smaller than M, and M, N, Z is a positive integer, the problem that the financial product combination is difficult to meet the requirements of a user when the financial product combination is determined by single specific data in the related art is solved, the characteristics are input into the model by acquiring a plurality of characteristics in the financial products, a profit result is obtained, the target financial product combination is determined by utilizing the profit result, and the financial product combination further achieves the effect of recommending the financial product combination required by the user.
Optionally, in the method for selecting financial products provided in the embodiment of the present application, obtaining M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products, obtaining the target financial data includes: acquiring M candidate financial products and financial reports of the M candidate financial products from a financial consultation website, and acquiring financial data of the financial products from the financial reports to obtain M financial data; preprocessing M financial data to M processed financial data, wherein the preprocessing mode at least comprises one of the following steps: standardized processing and filling of missing values; and for each processed financial data, respectively arranging the importance degrees of all the included financial feature data to obtain M financial feature data sequences, selecting the financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as target financial data.
Specifically, the financial data may include data such as index of dispersion, net asset yield, gross interest rate, asset liability list, and business income, and since the value of each financial data is greatly different, it is necessary to perform standardization processing on the financial data, and process the financial data into a positive number smaller than one.
Further, since the obtained original data may have a missing value of a feature, it is necessary to determine whether the normalized financial data has a missing value, and if the determination result indicates that the missing value exists, a default value or an average value of the financial data is filled in a missing value area to obtain a plurality of processed financial data, where the missing value refers to clustering, grouping, deleting or cutting of the data caused by missing information, so that a value of a certain attribute or some attribute in the existing data set is not complete.
Further, the plurality of financial feature data in the preprocessed financial data are arranged in a descending order of feature weights, and the financial feature data are selected according to the arrangement result, and fig. 2 is a schematic diagram of the financial feature data weights provided according to an embodiment of the present application, as shown in fig. 2, for example, the financial feature data may include average market rate, relationship return, account value, profit gain rate, expenditure, liabilities, income cash, amount, income, total assets, and the like, and after calculating the weight of each financial feature data, 5 data with the highest weight value is selected as target financial data.
Optionally, in the method for selecting a financial product provided in the embodiment of the present application, for each piece of processed financial data, the method includes the steps of: respectively inputting the M processed financial data into a sequencing model to obtain the weight value of each financial characteristic data of each processed financial data; descending order arrangement is carried out on the financial characteristic data in each processed financial data according to the magnitude relation of the weight values, so that M financial characteristic data sequences are obtained; selecting financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as target financial data comprises: and selecting a first preset number of feature data from each financial feature data sequence respectively, and combining the selected financial feature data into target financial data.
The financial characteristic data in the financial data is obtained by using a sorting model, and specifically, the preprocessed financial data is input into the sorting model, wherein the sorting model is a model for sorting characteristic weights based on a random forest model, the weight value of each financial characteristic data in each financial data can be obtained after all the financial data are input into the sorting model, the financial characteristic data in the sequence are sorted in reverse order according to the weight value of each financial characteristic data, and the financial characteristic data in the first third of the sequence are used as target financial data, so that the financial product combination with higher return is obtained.
Optionally, in the method for selecting a financial product provided by the embodiment of the present application, the N prediction models include N-1 sub-prediction models and an aggregate model obtained by aggregating the N-1 sub-prediction models, where the prediction models are obtained by training in the following manner: acquiring Y historical financial products, and processing financial data associated with the Y historical financial products to obtain Y sample data; using Y sample data as a training set, and training N-1 preset sub-prediction models by using the training set to obtain N-1 sub-prediction models; performing aggregation operation on the N-1 sub-prediction models by using an aggregation algorithm to obtain an initial aggregation model; and training an initial aggregation model by using Y sample data to obtain an aggregation model, and determining the aggregation model and the N-1 sub-prediction models as N prediction models under the condition that the aggregation model meets the reference model requirement, wherein the condition that the aggregation model meets the reference model requirement means that the parameters of the aggregation model meet the parameter requirement of the reference model.
For example, the prediction model may include three sub-prediction models and an aggregate model obtained by aggregating the sub-prediction models, where the three sub-prediction models may be a feedforward neural network model, a random forest model and an adaptive neural fuzzy inference model, and are obtained by training a plurality of sample data, specifically, financial data of a plurality of historical financial products are obtained from a financial consultation website, and the data is preprocessed to obtain a plurality of sample data, and is used as a training set to train three preset sub-prediction models, that is, the feedforward neural network model, the random forest model and the adaptive neural fuzzy inference model are trained by using the sample data, so as to obtain three trained sub-prediction models.
Further, the three trained sub-prediction models are subjected to aggregation operation by using a self-service aggregation algorithm to obtain an aggregation model, the aggregation model is subjected to sample data training to obtain a trained aggregation model, and the trained aggregation model and the three trained sub-prediction models are used as prediction models.
It should be noted that, whether the aggregate model is trained is judged by a reference model, specifically, the trained adaptive neural fuzzy inference model is used as the reference model, and the reference model is a reference model for measuring and evaluating the performances of the other models. And acquiring a first parameter of the trained self-adaptive neuro-fuzzy inference model by using a program framework, and adapting a sample data input value to the neuro-fuzzy inference model to obtain a second parameter, wherein the aggregation model accords with the reference model requirement under the condition that the parameter obtained by inputting the sample data to the aggregation model is larger than the first parameter and the second parameter, namely the training effect of the aggregation model is better than the output effect of the reference model, and the training is finished.
Optionally, in the method for selecting a financial product provided in the embodiment of the present application, determining a financial product combination according to a financial product that meets a preset requirement includes: screening target financial products from financial products meeting preset requirements according to the relative income to obtain Z target financial products; the Z target financial product combinations are financial product combinations.
Specifically, the preset requirement may refer to that the financial product needs to be located at the first third of all the arrangement sequences or before the financial product needs to be located at the preset number of positions of all the arrangement sequences, for example, if the arrangement sequences include 60 data in total, the preset requirement may be that the financial product needs to be arranged at the first 15 positions; each arrangement is obtained according to the relative income data corresponding to the financial products, and after the target financial products are obtained, the target financial products are evaluated to be combined into a financial product combination.
Optionally, in the method for selecting a financial product provided in the embodiment of the present application, selecting, according to relative yields, target financial products from financial products meeting preset requirements, to obtain Z target financial products includes: inputting target financial data of financial products meeting preset requirements into a sequencing model to obtain weight values of various financial characteristic data of each financial product in a target time period, and calculating the percentage of the weight value of each financial characteristic data to the total weight value; and calculating the fluctuation rate of each financial product in the target time period by using the percentage, and determining the financial product as the target financial product under the condition that the fluctuation rate is smaller than the fluctuation threshold value to obtain Z target financial products.
Specifically, inputting target financial data in financial products meeting arrangement requirements into three sub-prediction models and an aggregation model obtained by aggregating the three sub-prediction models to obtain a weight value of each financial characteristic data, and calculating the fluctuation rate deltax of each characteristic by using the percentage after the weight value of each financial characteristic data is calculated to be the percentage of the total weight value:
wherein x is t For a certain characteristic at time t, x t-1 This feature is the time t-1.
Further, under the condition that the fluctuation rate is smaller than the threshold value, the characteristic is indicated to be stable, the financial product corresponding to the characteristic is taken as a target financial product, further, the investment combination of the financial products is obtained, and the total income amount obtained according to the financial product combination is stable.
Optionally, in the method for selecting a financial product provided by the embodiment of the present application, the Z target financial product combinations are financial product combinations including: calculating the return rate of return according to the return result of each target financial product to obtain Z return rates of return, and calculating the summer ratio by using the Z return rates of return; judging whether the summer ratio is larger than a preset summer ratio threshold value or not; and under the condition that the summer ratio is smaller than or equal to a preset summer ratio threshold, re-determining Z target financial products from financial products meeting preset requirements in a target time period, and combining the re-determined Z target financial products into a financial product combination, wherein the summer ratio of the re-determined Z target financial products is larger than the preset summer ratio threshold.
Specifically, after obtaining the target return data of each target financial product, calculating the return rate R of each target financial product i(q) And calculates the actual relative benefit R using the following formula (q) ：
Wherein m is the number of all financial products acquired at this time.
Further, the average actual relative benefit is calculated using the following formula
Wherein z is the number of target financial products;
further, the summer ratio P is calculated using the following formula:
wherein sigma q Is the standard deviation of the target financial product for the target time period.
The summer ratio is used for displaying the return rate data after risk adjustment, so that investors can be helped to better know the income situation of stocks, when the summer ratio is larger than a preset value, the financial product combination is indicated to have lower risk and higher return, and when the summer ratio is smaller than a preset summer ratio threshold value, financial products except candidate financial products in the target time period are selected to be used as a second group of candidate financial products, preprocessed and input into a prediction model, and target financial products are selected according to the result output by the model; if the summer-back ratio is greater than the preset summer-back ratio threshold, the target financial product combination is used as the financial product combination, and the financial product combination is evaluated by utilizing the summer-back ratio, so that the better financial product combination can be obtained.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides a device for selecting the financial product, and the device for selecting the financial product can be used for executing the method for selecting the financial product provided by the embodiment of the application. The following describes a selection device of a financial product provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a selection device for a financial product according to an embodiment of the present application, as shown in fig. 3, the device includes: an acquisition unit 30, an input unit 31, a sorting unit 32, a judgment unit 33.
An obtaining unit 30, configured to obtain M candidate financial products in a target time period, and process financial data associated with the M candidate financial products to obtain target financial data;
an input unit 31, configured to input target financial data into N prediction models, and output N sets of revenue results, where each set of revenue results includes revenue results of M candidate financial products;
The sorting unit 32 is configured to sort, for each set of revenue results, the associated M candidate financial products according to the revenue results, so as to obtain N sorting results;
the judging unit 33 is configured to judge whether each financial product meets a preset requirement according to the N sorting results, and determine a financial product combination according to the financial products meeting the preset requirement, where the preset requirement is a sequence of the financial products in a pre-preset proportion before each sorting result, and the financial product combination includes Z target financial products, where Z is smaller than M and M, N, Z is a positive integer.
Alternatively, in the selecting device for a financial product provided in the embodiment of the present application, the acquiring unit 30 includes: the first acquisition module is used for acquiring M candidate financial products and financial reports of the M candidate financial products from the financial consultation website, and acquiring financial data of the financial products from the financial reports to obtain M financial data; the processing module is used for preprocessing M financial data to M processed financial data, wherein the preprocessing mode at least comprises one of the following steps: standardized processing and filling of missing values; the first arrangement module is used for arranging the importance degree of all the financial characteristic data contained in each processed financial data respectively to obtain M financial characteristic data sequences, selecting the financial characteristic data according to the M financial characteristic data sequences, and determining the selected financial characteristic data as target financial data.
Alternatively, in the selecting device for a financial product provided in the embodiment of the present application, the acquiring unit 30 includes: the first input module is used for respectively inputting the M processed financial data into the ordering model to obtain the weight value of each financial characteristic data of each processed financial data; the second arrangement module is used for carrying out descending order arrangement on the financial characteristic data in each processed financial data according to the magnitude relation of the weight values to obtain M financial characteristic data sequences; selecting financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as target financial data comprises: the selecting module is used for selecting a first preset number of feature data from each financial feature data sequence respectively and combining the selected financial feature data into target financial data.
Optionally, in the selecting device for a financial product provided in the embodiment of the present application, the N prediction models include N-1 sub-prediction models and an aggregate model obtained by aggregating the N-1 sub-prediction models, where the prediction models are obtained by training in the following manner: the second acquisition module is used for acquiring Y historical financial products and processing financial data associated with the Y historical financial products to obtain Y sample data; the first training module is used for taking Y sample data as a training set, and training N-1 preset sub-prediction models by using the training set to obtain N-1 sub-prediction models; the aggregation module is used for conducting aggregation operation on the N-1 sub-prediction models by utilizing an aggregation algorithm to obtain an initial aggregation model; the second training module is used for training the initial aggregation model by using Y sample data to obtain an aggregation model, and determining the aggregation model and the N-1 sub prediction models as N prediction models under the condition that the aggregation model meets the reference model requirement, wherein the condition that the aggregation model meets the reference model requirement means that the parameters of the aggregation model meet the parameter requirement of the reference model.
Optionally, in the selecting device for a financial product provided in the embodiment of the present application, the judging unit 33 includes: the screening module is used for screening target financial products from financial products meeting preset requirements according to the relative income to obtain Z target financial products; and the combination module is used for combining Z target financial products into a financial product combination.
Optionally, in the selecting device for a financial product provided in the embodiment of the present application, the judging unit 33 includes: the second input module is used for inputting target financial data of financial products meeting preset requirements into the ordering model, obtaining weight values of various financial characteristic data of each financial product in a target time period, and calculating the percentage of the weight value of each financial characteristic data to the total weight value; and the first calculation module is used for calculating the fluctuation rate of each financial product in the target time period by using the percentage, and determining the financial product as the target financial product under the condition that the fluctuation rate is smaller than the fluctuation threshold value to obtain Z target financial products.
Optionally, in the selecting device for a financial product provided in the embodiment of the present application, the judging unit 33 includes: the second calculation module is used for calculating the return rate according to the return result of each target financial product to obtain Z return rates, and calculating the summer ratio by utilizing the Z return rates; the judging module is used for judging whether the summer ratio is larger than a preset summer ratio threshold value or not; and the determining module is used for redetermining Z target financial products from the financial products meeting the preset requirement in the target time period under the condition that the summer ratio is smaller than or equal to the preset summer ratio threshold value, and combining the redetermined Z target financial products into a financial product combination, wherein the summer ratio of the redetermined Z target financial products is larger than the preset summer ratio threshold value.
According to the financial product selecting device provided by the embodiment of the application, the obtaining unit 30 is used for obtaining M candidate financial products in a target time period and processing financial data associated with the M candidate financial products to obtain target financial data; an input unit 31, configured to input target financial data into N prediction models, and output N sets of revenue results, where each set of revenue results includes revenue results of M candidate financial products; the sorting unit 32 is configured to sort, for each set of revenue results, the associated M candidate financial products according to the revenue results, so as to obtain N sorting results; the judging unit 33 is configured to judge whether each financial product meets a preset requirement according to N sorting results, and determine a financial product combination according to the financial products meeting the preset requirement, where the preset requirement is a sequence of the financial products in a pre-preset proportion of each sorting result, the financial product combination includes Z target financial products, Z is smaller than M and M, N, Z is a positive integer, so that the problem that when the financial product combination is determined by using single specific data in the related art, the financial product combination is difficult to meet the requirement of a user is solved, and by acquiring a plurality of features in the financial products, the features are input into the model to obtain a profit result, and the target financial product combination is determined by using the profit result, so that the effect of recommending the financial product combination for the user is achieved.
The selection device of the financial product includes a processor and a memory, the above-mentioned acquisition unit 30, input unit 31, sorting unit 32, judgment unit 33, etc. are stored as program units in the memory, and the above-mentioned program units stored in the memory are executed by the processor to realize the corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the problem that the financial product combination is difficult to meet the requirement of a user when the financial product combination is determined by single specific data in the related technology is solved by adjusting the kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
Embodiments of the present invention provide a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements a method of selecting a financial product.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute a financial product selection method.
Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 4, an embodiment of the present invention provides an electronic device, where an electronic device 40 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor is configured to execute computer readable instructions, where the computer readable instructions execute a method for selecting a financial product when executed. The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform a method of selecting a financial product when executed on a data processing apparatus.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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 memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. A method of selecting a financial product, comprising:
obtaining M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data;
inputting the target financial data into N prediction models respectively, and outputting N groups of income results, wherein each group of income results comprise income results of M candidate financial products;
for each group of income results, sorting the associated M candidate financial products according to the income results to obtain N sorting results;
judging whether each financial product meets a preset requirement according to the N sorting results, and determining a financial product combination according to the financial products meeting the preset requirement, wherein the preset requirement refers to a sequence of the financial products in a preset proportion before each sorting result, the financial product combination comprises Z target financial products, Z is smaller than M, and M, N, Z is a positive integer.
2. The method of claim 1, wherein obtaining M candidate financial products in a target time period and processing financial data associated with the M candidate financial products to obtain target financial data comprises:
Acquiring M candidate financial products and financial reports of the M candidate financial products from a financial consultation website, and acquiring financial data of the financial products from the financial reports to obtain M financial data;
preprocessing the M financial data to M processed financial data, wherein the preprocessing mode at least comprises one of the following steps: standardized processing and filling of missing values;
and for each processed financial data, respectively arranging the importance degrees of all the included financial feature data to obtain M financial feature data sequences, selecting the financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as the target financial data.
3. The method of claim 2, wherein for each processed financial data, ranking the importance levels of all financial feature data included separately to obtain M financial feature data sequences includes:
respectively inputting the M processed financial data into a sequencing model to obtain the weight value of each financial characteristic data of each processed financial data;
descending order arrangement is carried out on the financial characteristic data in each processed financial data according to the magnitude relation of the weight values, so that M financial characteristic data sequences are obtained;
Selecting financial feature data according to the M financial feature data sequences, and determining the selected financial feature data as the target financial data comprises:
and selecting a first preset number of feature data from each financial feature data sequence respectively, and combining the selected financial feature data into the target financial data.
4. The method according to claim 1, wherein the N prediction models comprise N-1 sub-prediction models and an aggregate model aggregated from the N-1 sub-prediction models, the prediction models being trained by:
acquiring Y historical financial products, and processing financial data associated with the Y historical financial products to obtain Y sample data;
using the Y sample data as a training set, and training N-1 preset sub-prediction models by using the training set to obtain the N-1 sub-prediction models;
performing aggregation operation on the N-1 sub-prediction models by using an aggregation algorithm to obtain an initial aggregation model;
and training the initial aggregation model by using the Y sample data to obtain an aggregation model, and determining the aggregation model and the N-1 sub-prediction models as the N prediction models under the condition that the aggregation model meets the reference model requirement, wherein the condition that the aggregation model meets the reference model requirement means that the parameters of the aggregation model meet the parameter requirement of the reference model.
5. The method of claim 1, wherein determining a combination of financial products from the financial products meeting the preset requirements comprises:
screening target financial products from the financial products meeting the preset requirements according to the relative yields to obtain Z target financial products;
the Z target financial product combinations are the financial product combinations.
6. The method of claim 5, wherein selecting target financial products from the financial products meeting the predetermined requirement based on relative yields comprises:
inputting target financial data of the financial products meeting the preset requirements into a sequencing model to obtain weight values of the financial characteristic data of each financial product in a target time period, and calculating the percentage of the weight value of each financial characteristic data to the total weight value;
and calculating the fluctuation rate of each financial product in the target time period by using the percentage, and determining the financial product as the target financial product under the condition that the fluctuation rate is smaller than a fluctuation threshold value to obtain the Z target financial products.
7. The method of claim 5, wherein the Z target combinations of financial products as the combination of financial products comprises:
Calculating the return rate of return according to the return results of each target financial product to obtain Z return rates of return, and calculating the summer ratio by utilizing the Z return rates of return;
judging whether the summer ratio is larger than a preset summer ratio threshold value or not;
and under the condition that the summer ratio is smaller than or equal to the preset summer ratio threshold, re-determining Z target financial products from the financial products meeting the preset requirement in the target time period, and combining the re-determined Z target financial products into the financial product combination, wherein the summer ratio of the re-determined Z target financial products is larger than the preset summer ratio threshold.
8. A financial product selection device, comprising:
the acquisition unit is used for acquiring M candidate financial products in a target time period, and processing financial data associated with the M candidate financial products to obtain target financial data;
the input unit is used for respectively inputting the target financial data into N prediction models and outputting N groups of income results, wherein each group of income results comprise income results of M candidate financial products;
The ordering unit is used for ordering the associated M candidate financial products according to the profit results to obtain N ordering results;
the judging unit is used for judging whether each financial product meets a preset requirement according to the N sorting results, and determining a financial product combination according to the financial products meeting the preset requirement, wherein the preset requirement is a sequence of the financial products in a preset proportion before each sorting result, the financial product combination comprises Z target financial products, Z is smaller than M, and M, N, Z is a positive integer.
9. A processor for running a program, wherein the program when run performs the method of selecting a financial product according to any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of selecting a financial product of any of claims 1-7.
CN202310450124.9A 2023-04-24 2023-04-24 Financial product selection method, device, processor and electronic equipment Pending CN116485537A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310450124.9A CN116485537A (en) 2023-04-24 2023-04-24 Financial product selection method, device, processor and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310450124.9A CN116485537A (en) 2023-04-24 2023-04-24 Financial product selection method, device, processor and electronic equipment

Publications (1)

Publication Number Publication Date
CN116485537A true CN116485537A (en) 2023-07-25

Family

ID=87211427

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310450124.9A Pending CN116485537A (en) 2023-04-24 2023-04-24 Financial product selection method, device, processor and electronic equipment

Country Status (1)

Country Link
CN (1) CN116485537A (en)

Similar Documents

Publication Publication Date Title
CN111291925A (en) Financial market prediction and decision-making system and method based on artificial intelligence
CN107679987A (en) Asset Allocation strategy acquisition methods, device, computer equipment and storage medium
CN111932044A (en) Steel product price prediction system and method based on machine learning
Etemadi et al. Earnings per share forecast using extracted rules from trained neural network by genetic algorithm
CN111667307A (en) Method and device for predicting financial product sales volume
CN111353626A (en) Data auditing method, device and equipment
CN114529400A (en) Consumption loan preauthorization evaluation method, device and medium
CN110599351A (en) Investment data processing method and device
Jiang et al. [Retracted] Research on Intelligent Prediction Method of Financial Crisis of Listed Enterprises Based on Random Forest Algorithm
US20210056625A1 (en) Artificial intelligence and machine learning in a clustering processes to develop a utility model for asset allocation and automated rebalancing of exchange traded funds
CA3160715A1 (en) Systems and methods for business analytics model scoring and selection
CN114741592B (en) Product recommendation method, device and medium based on multi-model fusion
CN116485526A (en) Service processing method and device and electronic equipment
CN116304929A (en) Financial manipulation recognition method and device based on A-stock market
CN115936184A (en) Load prediction matching method suitable for multi-user types
CN116485537A (en) Financial product selection method, device, processor and electronic equipment
Rodionov et al. Predicting the Probability of Bankruptcy of Service Sector Enterprises Based on Ensemble Learning Methods
CN106485363A (en) The one B shareB in a few days quantization of upward price trend and Forecasting Methodology
CN111581068A (en) Terminal workload calculation method and device, storage medium, terminal and cloud service system
Celina et al. Algorithm-driven predictive analysis of blue-chip stocks in the murky indian environment
Kumari et al. A Comparative Analysis of Data Standardization Methods on Stock Movement
CN117952688A (en) Classification method and device for merchants and electronic equipment
Li The predictability and analysis of CNY to USD exchange rate based on ARMA model
CN116862613A (en) Product recommendation method and device, storage medium and electronic equipment
CN117454272A (en) Method and device for issuing consumption ticket, storage medium and electronic equipment

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