CN113723525B - Product recommendation method, device, equipment and storage medium based on genetic algorithm - Google Patents
Product recommendation method, device, equipment and storage medium based on genetic algorithm Download PDFInfo
- Publication number
- CN113723525B CN113723525B CN202111017839.2A CN202111017839A CN113723525B CN 113723525 B CN113723525 B CN 113723525B CN 202111017839 A CN202111017839 A CN 202111017839A CN 113723525 B CN113723525 B CN 113723525B
- Authority
- CN
- China
- Prior art keywords
- data
- investment
- model
- information
- inputting
- 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.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 79
- 230000002068 genetic effect Effects 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000006870 function Effects 0.000 claims description 56
- 238000004364 calculation method Methods 0.000 claims description 28
- 230000004927 fusion Effects 0.000 claims description 28
- 238000001514 detection method Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 229940127554 medical product Drugs 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 229910005543 GaSe Inorganic materials 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention relates to the field of artificial intelligence and discloses a product recommendation method, device and equipment based on a genetic algorithm and a storage medium, wherein the method comprises the following steps: acquiring data stream information, wherein the data stream information comprises product information and customer information; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, inputting the first sample training data set into a preset genetic algorithm model for training, and obtaining an investment combination recommendation model; the data flow information and the prediction result are input into the investment portfolio recommendation model, the target recommended product is determined, and the target recommended product is sent to the client terminal, so that the flow direction condition of the cash flow data of the client is accurately predicted, intelligent investment product recommendation for the client is realized, and the accuracy and efficiency of product recommendation are improved. The present invention relates to blockchain techniques, such as writing data streams into blockchains for use in data forensics and other scenarios.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a product recommendation method, device, equipment and storage medium based on a genetic algorithm.
Background
At present, less software is used for accurately predicting future cash flow conditions of enterprises through a big data model in the market, and meanwhile, in different product recommendation scenes, because the product data on a big data platform are very large, the product recommendation technology is difficult to realize, so that less software is used for intelligently recommending investment product service schemes for enterprises. Therefore, how to achieve efficient, accurate and intelligent product recommendation is a major issue.
Disclosure of Invention
The embodiment of the invention provides a product recommending method, device, equipment and storage medium based on a genetic algorithm, which can accurately predict the flow direction condition of cash flow data of a customer, realize intelligent investment product recommending for the customer and improve the accuracy and efficiency of product recommending.
In a first aspect, an embodiment of the present invention provides a product recommendation method based on a genetic algorithm, including:
obtaining data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information associated with each product, which is obtained from one or more of an enterprise big data platform, an external data platform and a bank big data platform;
Inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information;
acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model;
and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal.
Further, before inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information, the method further includes:
obtaining a second sample training dataset comprising a plurality of historical cash flow data;
inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the time sequence prediction model, and inputting the second sample training data set into the time sequence prediction model with the model parameters adjusted for iterative training;
And when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, after the second sample training data set is obtained, the method further includes:
preprocessing each historical cash flow data in the second sample training data set, and detecting stability of the preprocessed second sample training data set;
if the stability detection is not passed, carrying out differential processing on the preprocessed second sample training data set;
when the stability detection passes after the differential processing is executed for a plurality of times, performing white noise detection processing on the second sample training data set after the differential processing;
when the white noise test fails, performing autocorrelation calculation and partial autocorrelation calculation on the second sample training data set after the differential processing to obtain first result data of the autocorrelation calculation and second result data of the partial autocorrelation calculation;
the step of inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value comprises the following steps:
and inputting the second sample training data set, the times of differential processing, the first result data and the second result data into a pre-trained time sequence prediction model to obtain the loss function value.
Further, before inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information, the method further includes:
inputting the second sample training data set into a pre-trained business rule prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the business rule prediction model, and inputting the second sample training data set into the business rule prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, before inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information, the method further includes:
carrying out fusion processing on the time sequence prediction model and the business rule prediction model according to a preset fusion rule to obtain a fusion prediction model;
inputting the second sample training data set into the fusion prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the fusion prediction model, and inputting the second sample training data set into the fusion prediction model with the model parameters adjusted for iterative training;
And when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, the inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment portfolio recommendation model includes:
acquiring combined investment ratio data between each product from each historical investment data in the first sample training data set, and individual investment ratio data of each product;
converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data;
combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data;
and selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
Further, the inputting the data flow information and the prediction result into a portfolio recommendation model to determine a target recommended product includes:
Acquiring attribute information of product information in the data stream information, and classifying each product according to the attribute information;
and inputting the classified data flow information and the prediction result into the investment portfolio recommendation model to determine the target recommended product.
In a second aspect, an embodiment of the present invention provides a product recommendation device based on a genetic algorithm, including:
the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring data flow information, the data flow information comprises product information and customer information, and the data flow information is data information which is acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform and is associated with each product;
the prediction unit is used for inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information;
the training unit is used for acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model;
And the recommending unit is used for inputting the data flow information and the prediction result into a investment portfolio recommending model, determining a target recommended product and sending the target recommended product to a client terminal.
In a third aspect, an embodiment of the present invention provides a computer device, including a processor and a memory, where the memory is configured to store a computer program, the computer program including a program, and the processor is configured to invoke the computer program to perform the method of the first aspect.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program for execution by a processor to implement the method of the first aspect.
The embodiment of the invention can acquire the data stream information, wherein the data stream information comprises product information and customer information, and the data stream information is data information associated with each product acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal. By the implementation mode, the flow direction condition of the cash flow data of the customer can be accurately predicted, intelligent investment product recommendation for the customer is realized, and the accuracy and efficiency of product recommendation are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a product recommendation method based on a genetic algorithm provided by an embodiment of the invention;
FIG. 2 is a schematic block diagram of a product recommendation device based on a genetic algorithm according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The product recommendation method based on the genetic algorithm provided by the embodiment of the invention can be applied to a product recommendation device based on the genetic algorithm, and in some embodiments, the product recommendation device based on the genetic algorithm is arranged in computer equipment. In certain embodiments, the computer device includes, but is not limited to, one or more of a smart phone, tablet, laptop, etc.
The embodiment of the invention can acquire the data stream information, wherein the data stream information comprises product information and customer information, and the data stream information is data information associated with each product acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal. By the implementation mode, the flow direction condition of the cash flow data of the customer can be accurately predicted, intelligent investment product recommendation for the customer is realized, and the accuracy and efficiency of product recommendation are improved.
The embodiment of the application can acquire and process related data (such as data stream information) based on artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The embodiment of the application can be applied to various fields, such as: medical product recommendation fields, financial product recommendation fields, and the like.
In one possible implementation, the data may be medical data associated with a medical product, such as inspection data, assay data, etc. associated with the medical product, in the medical product recommendation field.
The following describes a product recommendation method based on a genetic algorithm according to an embodiment of the present invention schematically with reference to fig. 1.
Referring to fig. 1, fig. 1 is a schematic flowchart of a product recommendation method based on a genetic algorithm according to an embodiment of the present invention, and as shown in fig. 1, the method may be performed by a product recommendation device based on a genetic algorithm, where the product recommendation device based on a genetic algorithm is disposed in a computer device. Specifically, the method of the embodiment of the invention comprises the following steps.
S101: and acquiring data stream information, wherein the data stream information comprises product information and client information.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can acquire the data stream information, wherein the data stream information comprises the product information and the client information. In some embodiments, the data stream information may be data information associated with each product obtained from one or more of an enterprise big data platform, an external data platform, a bank big data platform. In certain embodiments, the data stream information includes, but is not limited to, enterprise production management data, market data, banking data, and the like.
S102: inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can input the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information. In some embodiments, the forecast includes a forecast of whether cash for each product is surplus or shortage, how much surplus or shortage is, etc. for a future period of time.
In one embodiment, the genetic algorithm-based product recommendation device may acquire a second sample training data set before inputting the data stream information into the pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information, where the second sample training data set includes a plurality of historical cash stream data; inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value; when the loss function value does not meet the preset condition, adjusting the model parameters of the time sequence prediction model, and inputting the second sample training data set into the time sequence prediction model with the model parameters adjusted for iterative training; and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model. In some embodiments, the time series prediction model may be an arima differential integration moving average autoregressive model.
In one embodiment, the genetic algorithm-based product recommendation device may process a plurality of historical cash flow data in the second sample training data set prior to inputting the second sample training data set into the pre-trained time series prediction model.
In one embodiment, when the product recommendation device based on the genetic algorithm processes the plurality of historical cash flow data in the second sample training data set, operations such as missing filling and abnormality detection can be performed on each of the historical cash flow data, so as to fill in missing data, process or delete abnormal data, and the like.
In one embodiment, the product recommendation device based on the genetic algorithm may perform trend analysis on each of the historical cash flow data when processing the multi-historical cash flow data in the second sample training data set, and determine a long-term trend, a seasonal trend, a periodic trend, an irregular variation trend, and the like according to each of the historical cash flow data.
In some embodiments, the long-term trend refers to some sort of continuously rising or continuously falling variation that the time series exhibits over a long period of time, which may be linear or nonlinear; seasonal trend refers to regular periodic variations that occur over the course of a year as the seasons change; the periodic trend refers to the regular variation of the undulating form exhibited by the wave over a period of several years (non-stationary period); the irregular variation trend refers to an irregularly and circularly-shaped variation, and comprises two types of strict random variation and variation with great influence of irregularity and burstiness.
In one embodiment, after the second sample training data set is acquired, the product recommendation device based on the genetic algorithm may perform preprocessing on each historical cash flow data in the second sample training data set, and perform stationarity detection on the preprocessed second sample training data set; if the stability detection is not passed, carrying out differential processing on the preprocessed second sample training data set; when the stability detection passes after the differential processing is executed for a plurality of times, performing white noise detection processing on the second sample training data set after the differential processing; and when the white noise test fails, performing autocorrelation calculation and partial autocorrelation calculation on the second sample training data set after the differential processing to obtain first result data of the autocorrelation calculation and second result data of the partial autocorrelation calculation.
In one embodiment, the calculation formula of the autocorrelation calculation is shown in the following formula (1):
where covariance γ (s, t) = cov (x s ,x t )＝E[(x s -μ s )(x t -μ t ) From the Cauchy-Schwarz inequality, it is known that-1.ltoreq.ρ (s, t). Ltoreq.1.
Let s=t+h, γ (t+h, t) = cov (x t+h ,x t ) If the time series x is stationary, the covariance is independent of the time t.
cov(x t+h ,x t )＝cov(x h ,x 0 ) The second parameter, denoted γ (h), is generally omitted, and the autocorrelation function of the stationary sequence can be reduced to the following formula (2):
in one embodiment, the partial autocorrelation differs from the autocorrelation in that the autocorrelation is a direct calculation of x t And x t+h Correlation between them, partial autocorrelation is the calculation of x t And x t+h Correlation between them, but remove { x } between them t+h ,…,x t+h-1 Linear dependence of }. The calculation formula of the partial autocorrelation calculation is shown in the following formula (3):
φ 11 ＝corr(x 1 ,x 0 )＝ρ(1)
wherein phi is used hh Representing the partial auto-correlation of the signal,is { x } 1 ,x 2 ,…,x h-1 [ X ] 0 Regression estimation of->Is { x } 1 ,x 2 ,…,x h-1 [ X ] 0 Is a regression estimate of (2).
If p and q are determined, the next step is to determine the coefficients of each itemθ 1 ,…, q And +.>The specific formula (4) is as follows:
the general common methods of parameter estimation are least square estimation and maximum likelihood estimation, wherein the least square estimation is implemented by searching a group of estimated values to make the distance between an actual value and the estimated value minimum, and the absolute value is troublesome to find the minimum mathematically, so that the sum of squares of differences between the actual value and the estimated value is minimum, and the method is specifically shown as the following formula (5):
in solving, the above square sum formula is usually used for deriving the parameter, and the first derivative is set to be zero, so as to obtain the value of the optimal parameter.
Maximum likelihood estimation maximizes the probability of a sample occurring by finding a set of parameters. Since the joint probability of all observations of the sample is maximized, the sample is in the form of a product of one-to-two, and can be changed into a linear sum form by taking the logarithm, and the method is specifically shown in the following formula (6):
when solving, the sum of the upper linear sum is usually used for deriving the parameters, and the first derivative is zero to obtain the value of the optimal parameter.
In one embodiment, when the second sample training data set is input into a pre-trained time series prediction model to obtain a loss function value, the product recommendation device based on the genetic algorithm may input the second sample training data set, the number of times of the differential processing, the first result data and the second result data into the pre-trained time series prediction model to obtain the loss function value.
In one example, assuming that the number of times of the differential processing is d, the first result data obtained by the autocorrelation calculation is p, the second result data obtained by the partial autocorrelation calculation is q, and the time-series prediction model is an ARIMA model, wherein ARIMA (p, d, q) is determined based on two basic models AR (p) and MA (q).
Wherein AR (p) is represented by the following formula (7):
MA (q) is represented by the following formula (8):
x t ＝w t +θ 1 w t-1 +θ 2 w t-2 +…+θ q w t-q (8)
combining AR (p) and MA (q) is ARMA (p, q), as shown in formula (9) below:
in one embodiment, the product recommendation device based on the genetic algorithm may input the second sample training data set into a pre-trained business rule prediction model to obtain a loss function value before inputting the data stream information into the pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; when the loss function value does not meet the preset condition, adjusting the model parameters of the business rule prediction model, and inputting the second sample training data set into the business rule prediction model with the model parameters adjusted for iterative training; and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
In one embodiment, the product recommendation device based on the genetic algorithm may perform fusion processing on the time sequence prediction model and the business rule prediction model according to a preset fusion rule before inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information, so as to obtain a fusion prediction model; inputting the second sample training data set into the fusion prediction model to obtain a loss function value; when the loss function value does not meet the preset condition, adjusting the model parameters of the fusion prediction model, and inputting the second sample training data set into the fusion prediction model with the model parameters adjusted for iterative training; and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
In an embodiment, the preset fusion rule may be the formula c=w×a+ (1-w) B, where w is a weight, a is a time sequence prediction model, B is a business rule prediction model, and when the product recommendation device based on the genetic algorithm performs fusion processing on the time sequence prediction model and the business rule prediction model according to the preset fusion rule, the product recommendation device may obtain a fusion prediction model according to the formula c=w×a+ (1-w) B.
S103: and acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can acquire a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and the first sample training data set is input into a preset genetic algorithm model for training to obtain an investment combination recommendation model.
In one embodiment, the product recommendation device based on the genetic algorithm may acquire the combined investment proportion data between each product and the individual investment proportion data of each product from each historical investment data in the first sample training data set when inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data; combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data; and selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
In one embodiment, the genetic algorithm-based product recommendation device may determine a congestion distance between the consolidated investment data according to the ordered consolidated investment data and select one or more target investment data according to the congestion distance when selecting one or more target investment data according to the ordered consolidated investment data. In some embodiments, the crowding distance refers to the density of consolidated investment data within a specified area, with a greater crowding distance for a consolidated investment data representing a smaller amount of surrounding other consolidated investment data.
In an embodiment, when the product recommendation device based on the genetic algorithm inputs the first sample training data set into a preset genetic algorithm model to train to obtain the investment portfolio recommendation model, the product recommendation device based on the genetic algorithm can also be obtained by training based on the Markov mean variance investment theory and the preset genetic algorithm.
S104: and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can input the data flow information and the prediction result into the investment portfolio recommendation model, determine the target recommended product and send the target recommended product to the client terminal.
In one embodiment, the product recommendation device based on the genetic algorithm may acquire attribute information of product information in the data stream information and classify each product according to the attribute information when inputting the data stream information and the prediction result into the investment portfolio recommendation model to determine a target recommended product; and inputting the classified data flow information and the prediction result into the investment portfolio recommendation model to determine the target recommended product.
In some embodiments, the classification result obtained by classifying each product may be an investment product, where the investment product may be classified into a short term, a medium term, a long term according to an investment period, and may be classified into a conservative type, a robust type, an access type, etc. according to an investment risk.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can acquire data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information related to each product acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal. By the implementation mode, the flow direction condition of the cash flow data of the customer can be accurately predicted, intelligent investment product recommendation for the customer is realized, and the accuracy and efficiency of product recommendation are improved.
The embodiment of the invention also provides a product recommendation device based on the genetic algorithm, which is used for executing the unit of the method of any one of the above. Specifically, referring to fig. 2, fig. 2 is a schematic block diagram of a product recommendation device based on a genetic algorithm according to an embodiment of the present invention. The product recommendation device based on the genetic algorithm of the embodiment includes: acquisition unit 201, prediction unit 202, training unit 203, and recommendation unit 204.
An obtaining unit 201, configured to obtain data flow information, where the data flow information includes product information and customer information, and the data flow information is data information associated with each product, which is obtained from one or more of an enterprise big data platform, an external data platform, and a bank big data platform;
a prediction unit 202, configured to input the data stream information into a pre-trained cash stream prediction model, and obtain a prediction result of cash stream data in the data stream information;
the training unit 203 is configured to obtain a first sample training data set, where the first sample training data set includes historical investment data of a plurality of products, and input the first sample training data set into a preset genetic algorithm model for training, so as to obtain an investment portfolio recommendation model;
And a recommending unit 204, configured to input the data stream information and the prediction result into a portfolio recommending model, determine a target recommended product, and send the target recommended product to a client terminal.
Further, before the prediction unit 202 inputs the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the prediction unit is further configured to:
obtaining a second sample training dataset comprising a plurality of historical cash flow data;
inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the time sequence prediction model, and inputting the second sample training data set into the time sequence prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, after the prediction unit 202 obtains the second sample training data set, the prediction unit is further configured to:
preprocessing each historical cash flow data in the second sample training data set, and detecting stability of the preprocessed second sample training data set;
If the stability detection is not passed, carrying out differential processing on the preprocessed second sample training data set;
when the stability detection passes after the differential processing is executed for a plurality of times, performing white noise detection processing on the second sample training data set after the differential processing;
when the white noise test fails, performing autocorrelation calculation and partial autocorrelation calculation on the second sample training data set after the differential processing to obtain first result data of the autocorrelation calculation and second result data of the partial autocorrelation calculation;
the step of inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value comprises the following steps:
and inputting the second sample training data set, the times of differential processing, the first result data and the second result data into a pre-trained time sequence prediction model to obtain the loss function value.
Further, before the prediction unit 202 inputs the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the prediction unit is further configured to:
inputting the second sample training data set into a pre-trained business rule prediction model to obtain a loss function value;
When the loss function value does not meet the preset condition, adjusting the model parameters of the business rule prediction model, and inputting the second sample training data set into the business rule prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, before the prediction unit 202 inputs the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the prediction unit is further configured to:
carrying out fusion processing on the time sequence prediction model and the business rule prediction model according to a preset fusion rule to obtain a fusion prediction model;
inputting the second sample training data set into the fusion prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the fusion prediction model, and inputting the second sample training data set into the fusion prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, the training unit 203 inputs the first sample training data set into a preset genetic algorithm model for training, and is specifically configured to:
acquiring combined investment ratio data between each product from each historical investment data in the first sample training data set, and individual investment ratio data of each product;
converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data;
combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data;
and selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
Further, the recommending unit 204 inputs the data flow information and the prediction result into a portfolio recommending model, and is specifically configured to:
acquiring attribute information of product information in the data stream information, and classifying each product according to the attribute information;
And inputting the classified data flow information and the prediction result into the investment portfolio recommendation model to determine the target recommended product.
In the embodiment of the invention, the product recommendation device based on the genetic algorithm can acquire data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information related to each product acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal. By the implementation mode, the flow direction condition of the cash flow data of the customer can be accurately predicted, intelligent investment product recommendation for the customer is realized, and the accuracy and efficiency of product recommendation are improved.
Referring to fig. 3, fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present invention, and in some embodiments, the computer device according to the present embodiment shown in fig. 3 may include: one or more processors 301; one or more input devices 302, one or more output devices 303, and a memory 304. The processor 301, the input device 302, the output device 303, and the memory 304 are connected via a bus 305. The memory 304 is used for storing a computer program comprising a program, and the processor 301 is used for executing the program stored in the memory 304. Wherein the processor 301 is configured to invoke the program execution:
obtaining data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information associated with each product, which is obtained from one or more of an enterprise big data platform, an external data platform and a bank big data platform;
inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information;
acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model;
And inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal.
Further, before inputting the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the processor 301 is further configured to:
obtaining a second sample training dataset comprising a plurality of historical cash flow data;
inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the time sequence prediction model, and inputting the second sample training data set into the time sequence prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, after the processor 301 obtains the second sample training data set, the processor is further configured to:
preprocessing each historical cash flow data in the second sample training data set, and detecting stability of the preprocessed second sample training data set;
If the stability detection is not passed, carrying out differential processing on the preprocessed second sample training data set;
when the stability detection passes after the differential processing is executed for a plurality of times, performing white noise detection processing on the second sample training data set after the differential processing;
when the white noise test fails, performing autocorrelation calculation and partial autocorrelation calculation on the second sample training data set after the differential processing to obtain first result data of the autocorrelation calculation and second result data of the partial autocorrelation calculation;
the step of inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value comprises the following steps:
and inputting the second sample training data set, the times of differential processing, the first result data and the second result data into a pre-trained time sequence prediction model to obtain the loss function value.
Further, before inputting the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the processor 301 is further configured to:
inputting the second sample training data set into a pre-trained business rule prediction model to obtain a loss function value;
When the loss function value does not meet the preset condition, adjusting the model parameters of the business rule prediction model, and inputting the second sample training data set into the business rule prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, before inputting the data stream information into the pre-trained cash stream prediction model to obtain the prediction result of the cash stream data in the data stream information, the processor 301 is further configured to:
carrying out fusion processing on the time sequence prediction model and the business rule prediction model according to a preset fusion rule to obtain a fusion prediction model;
inputting the second sample training data set into the fusion prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the fusion prediction model, and inputting the second sample training data set into the fusion prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
Further, when the processor 301 inputs the first sample training data set into a preset genetic algorithm model to train to obtain a portfolio recommendation model, the method is specifically used for:
acquiring combined investment ratio data between each product from each historical investment data in the first sample training data set, and individual investment ratio data of each product;
converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data;
combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data;
and selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
Further, the processor 301 inputs the data flow information and the prediction result into a portfolio recommendation model, and is specifically configured to:
acquiring attribute information of product information in the data stream information, and classifying each product according to the attribute information;
And inputting the classified data flow information and the prediction result into the investment portfolio recommendation model to determine the target recommended product.
In the embodiment of the invention, the computer equipment can acquire data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information related to each product acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform; inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information; acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model; and inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal. By the implementation mode, the flow direction condition of the cash flow data of the customer can be accurately predicted, intelligent investment product recommendation for the customer is realized, and the accuracy and efficiency of product recommendation are improved.
It should be appreciated that in embodiments of the present invention, the processor 301 may be a central processing unit (CenSral Processing UniS, CPU), which may also be other general purpose processors, digital signal processors (DigiSal Signal Processor, DSPs), application Specific Integrated Circuits (ASICs), off-the-shelf programmable gate arrays (Field-Programmable GaSe Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 302 may include a touch pad, a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.
The memory 304 may include read only memory and random access memory and provides instructions and data to the processor 301. A portion of memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information of device type.
In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present invention may execute the implementation described in the embodiment of the method described in fig. 1 provided in the embodiments of the present invention, and may also execute the implementation of the product recommendation device based on the genetic algorithm described in fig. 2 in the embodiments of the present invention, which is not described herein again.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the product recommendation method based on the genetic algorithm described in the embodiment corresponding to fig. 1 is implemented, and the product recommendation device based on the genetic algorithm in the embodiment corresponding to fig. 2 is also implemented, which is not described herein again.
The computer readable storage medium may be an internal storage unit of the genetic algorithm-based product recommendation apparatus according to any of the foregoing embodiments, for example, a hard disk or a memory of the genetic algorithm-based product recommendation apparatus. The computer readable storage medium may be an external storage device of the genetic algorithm-based product recommendation device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the genetic algorithm-based product recommendation device. Further, the computer-readable storage medium may further include both an internal storage unit and an external storage device of the genetic algorithm-based product recommendation apparatus. The computer readable storage medium is used for storing the computer program and other programs and data required by the product recommendation device based on the genetic algorithm. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a computer-readable storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes. The computer readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
It is emphasized that to further guarantee the privacy and security of the data, the data may also be stored in a blockchain node. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention.
Claims (9)
1. A product recommendation method based on a genetic algorithm, comprising:
obtaining data flow information, wherein the data flow information comprises product information and customer information, and the data flow information is data information associated with each product, which is obtained from one or more of an enterprise big data platform, an external data platform and a bank big data platform;
Inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information;
acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model;
inputting the data flow information and the prediction result into an investment portfolio recommendation model, determining a target recommended product, and sending the target recommended product to a client terminal;
inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment portfolio recommendation model, wherein the method comprises the following steps:
acquiring combined investment ratio data between each product from each historical investment data in the first sample training data set, and individual investment ratio data of each product;
converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data;
combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data;
And selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
2. The method of claim 1, wherein said inputting said data stream information into a pre-trained cash stream prediction model, prior to obtaining a prediction of cash stream data in said data stream information, further comprises:
obtaining a second sample training dataset comprising a plurality of historical cash flow data;
inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the time sequence prediction model, and inputting the second sample training data set into the time sequence prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
3. The method of claim 2, wherein after the obtaining the second sample training data set, further comprising:
Preprocessing each historical cash flow data in the second sample training data set, and detecting stability of the preprocessed second sample training data set;
if the stability detection is not passed, carrying out differential processing on the preprocessed second sample training data set;
when the stability detection passes after the differential processing is executed for a plurality of times, performing white noise detection processing on the second sample training data set after the differential processing;
when the white noise test fails, performing autocorrelation calculation and partial autocorrelation calculation on the second sample training data set after the differential processing to obtain first result data of the autocorrelation calculation and second result data of the partial autocorrelation calculation;
the step of inputting the second sample training data set into a pre-trained time sequence prediction model to obtain a loss function value comprises the following steps:
and inputting the second sample training data set, the times of differential processing, the first result data and the second result data into a pre-trained time sequence prediction model to obtain the loss function value.
4. The method of claim 2, wherein said inputting said data stream information into a pre-trained cash stream prediction model, prior to obtaining a prediction of cash stream data in said data stream information, further comprises:
Inputting the second sample training data set into a pre-trained business rule prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the business rule prediction model, and inputting the second sample training data set into the business rule prediction model with the model parameters adjusted for iterative training;
and when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
5. The method of claim 4, wherein said inputting said data stream information into a pre-trained cash stream prediction model, prior to obtaining a prediction of cash stream data in said data stream information, further comprises:
carrying out fusion processing on the time sequence prediction model and the business rule prediction model according to a preset fusion rule to obtain a fusion prediction model;
inputting the second sample training data set into the fusion prediction model to obtain a loss function value;
when the loss function value does not meet the preset condition, adjusting the model parameters of the fusion prediction model, and inputting the second sample training data set into the fusion prediction model with the model parameters adjusted for iterative training;
And when the loss function value obtained through iterative training meets a preset condition, determining to obtain the cash flow prediction model.
6. The method of claim 1, wherein said inputting the data flow information and the predicted outcome into a portfolio recommendation model determines a target recommended product, comprising:
acquiring attribute information of product information in the data stream information, and classifying each product according to the attribute information;
and inputting the classified data flow information and the prediction result into the investment portfolio recommendation model to determine the target recommended product.
7. A genetic algorithm-based product recommendation apparatus, comprising:
the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring data flow information, the data flow information comprises product information and customer information, and the data flow information is data information which is acquired from one or more of an enterprise big data platform, an external data platform and a bank big data platform and is associated with each product;
the prediction unit is used for inputting the data stream information into a pre-trained cash stream prediction model to obtain a prediction result of cash stream data in the data stream information;
The training unit is used for acquiring a first sample training data set, wherein the first sample training data set comprises historical investment data of a plurality of products, and inputting the first sample training data set into a preset genetic algorithm model for training to obtain an investment combination recommendation model;
the recommending unit is used for inputting the data stream information and the prediction result into a investment portfolio recommending model, determining a target recommended product and sending the target recommended product to a client terminal;
the training unit inputs the first sample training data set into a preset genetic algorithm model for training, and is specifically used for when the investment combination recommendation model is obtained:
acquiring combined investment ratio data between each product from each historical investment data in the first sample training data set, and individual investment ratio data of each product;
converting the combined investment proportion data and the independent investment proportion data of each product to obtain converted investment data;
combining the historical investment data with the conversion investment data to obtain combined investment data, and sequencing the combined investment data;
And selecting one or more target investment data according to the sorted combined investment data, and inputting the one or more target investment data into the preset genetic algorithm model for training to obtain the investment portfolio recommendation model.
8. A computer device comprising a processor and a memory, wherein the memory is for storing a computer program, the processor being configured to invoke the computer program to perform the method of any of claims 1-6.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111017839.2A CN113723525B (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111017839.2A CN113723525B (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113723525A CN113723525A (en) | 2021-11-30 |
| CN113723525B true CN113723525B (en) | 2024-02-20 |
Family
ID=78680216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111017839.2A Active CN113723525B (en) | 2021-08-31 | 2021-08-31 | Product recommendation method, device, equipment and storage medium based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723525B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118096223A (en) * | 2024-04-23 | 2024-05-28 | 紫金诚征信有限公司 | Financial product marketing method and device based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780140A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司 | Electric power credit assessment method based on big data |
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN111784449A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Data pushing method, data pushing equipment, storage medium and device |
| CN112150291A (en) * | 2020-09-08 | 2020-12-29 | 广元量知汇科技有限公司 | Intelligent financial product recommendation system |
| CN112613997A (en) * | 2020-12-17 | 2021-04-06 | 平安消费金融有限公司 | Method and apparatus for forecasting combined investment of money fund |
| CN112734516A (en) * | 2020-12-31 | 2021-04-30 | 中国工商银行股份有限公司 | Financial product recommendation method and system based on client cash flow prediction |
-
2021
- 2021-08-31 CN CN202111017839.2A patent/CN113723525B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780140A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司 | Electric power credit assessment method based on big data |
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN111784449A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Data pushing method, data pushing equipment, storage medium and device |
| CN112150291A (en) * | 2020-09-08 | 2020-12-29 | 广元量知汇科技有限公司 | Intelligent financial product recommendation system |
| CN112613997A (en) * | 2020-12-17 | 2021-04-06 | 平安消费金融有限公司 | Method and apparatus for forecasting combined investment of money fund |
| CN112734516A (en) * | 2020-12-31 | 2021-04-30 | 中国工商银行股份有限公司 | Financial product recommendation method and system based on client cash flow prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113723525A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aggarwal et al. | A complete empirical ensemble mode decomposition and support vector machine-based approach to predict Bitcoin prices | |
| CN110443692B (en) | Enterprise credit auditing method, device, equipment and computer readable storage medium | |
| Boto‐Giralda et al. | Wavelet‐based denoising for traffic volume time series forecasting with self‐organizing neural networks | |
| Ahuja et al. | Stock market forecast using sentiment analysis | |
| CN113011895B (en) | Associated account sample screening method, device and equipment and computer storage medium | |
| CN101681448A (en) | Information processing device, information processing method, and program | |
| Kumar et al. | Credit score prediction system using deep learning and k-means algorithms | |
| CN113723525B (en) | Product recommendation method, device, equipment and storage medium based on genetic algorithm | |
| CN113886697A (en) | Clustering algorithm based activity recommendation method, device, equipment and storage medium | |
| CN112990989A (en) | Value prediction model input data generation method, device, equipment and medium | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| CN117235633A (en) | Mechanism classification method, mechanism classification device, computer equipment and storage medium | |
| CN116402625A (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| Rosolia et al. | Analyzing deep generated financial time series for various asset classes | |
| CN113706258B (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
| Yan et al. | A CNN-based fingerprint image quality assessment method | |
| CN117312991B (en) | Method for constructing classification recognition system and related equipment thereof | |
| CN117172632B (en) | Enterprise abnormal behavior detection method, device, equipment and storage medium | |
| Valiakos et al. | Tuning the data sample for data envelopment analysis | |
| Acula | Classification of Disaster Risks in the Philippines using Adaptive Boosting Algorithm with Decision Trees and Support Vector Machine as Based Estimators | |
| Baranidharan et al. | Prediction and Analysis of Financial Crises Using Machine Learning | |
| JP6964540B2 (en) | Information processing equipment, information processing methods, and information processing programs | |
| Seba et al. | Density Based Regularization Model for Effective Forecasting of Stage Transition in Chronic Kidney Disease | |
| CA3108609A1 (en) | System and method for machine learning based detection of fraud | |
| Ivanenko | Assessing Social Media’s Impact on Stock Market Predictions: Financial Sentiment Embedding Approaches |
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 |