CN113052689B - Product recommendation method and device based on decision tree - Google Patents
Product recommendation method and device based on decision tree Download PDFInfo
- Publication number
- CN113052689B CN113052689B CN202110486328.9A CN202110486328A CN113052689B CN 113052689 B CN113052689 B CN 113052689B CN 202110486328 A CN202110486328 A CN 202110486328A CN 113052689 B CN113052689 B CN 113052689B
- Authority
- CN
- China
- Prior art keywords
- product
- client
- decision tree
- tested
- risk bearing
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012549 training Methods 0.000 claims description 25
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q30/018—Certifying business or products
-
- 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
-
- 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)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a product recommendation method and device based on decision trees, which are used for acquiring characteristics of clients to be tested, inputting the characteristics into the decision tree corresponding to each product aiming at each product to obtain client risk bearing grades of each product, wherein the decision tree is pre-constructed based on corresponding relations among client risk bearing grades, characteristics and characteristic duty ratios of sample clients, and the higher the client risk bearing grade is, the stronger the risk bearing capacity of the clients to be tested is. And taking the product with the risk bearing grade of the customer being greater than the preset grade as the product recommended to the customer to be tested. By using the method, based on the pre-constructed decision tree, the client risk bearing grade of each product can be accurately estimated, the products are recommended to the client to be tested according to the client risk bearing grade, and the products recommended to the client to be tested can be ensured to meet the self risk bearing capacity.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to a product recommendation method and device based on a decision tree.
Background
After purchasing a product recommended by a bank, the customer may not be able to bear the risk of purchasing the product due to the influence of the customer's own factors, thereby causing unpredictable results and causing great negative effects to the bank and the customer.
For this reason, how to recommend products satisfying their own risk-bearing capacity to customers is a problem to be solved in the art.
Disclosure of Invention
The application provides a product recommendation method and device based on a decision tree, and aims to recommend products meeting own risk bearing capacity to customers.
In order to achieve the above object, the present application provides the following technical solutions:
a decision tree based product recommendation method comprising:
acquiring characteristics of a customer to be tested;
inputting the characteristics into a decision tree corresponding to each product to obtain a customer risk bearing grade of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client is, the stronger the risk bearing capacity of the client to be tested is;
and taking the product with the risk bearing grade of the customer being greater than a preset grade as a product recommended to the customer to be tested.
Optionally, the decision tree is pre-built based on a correspondence between a client risk tolerance level, a feature, and a feature duty ratio of the sample client, and includes:
acquiring sample customer information of the product;
analyzing the sample client information to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; wherein the characteristic duty cycle characterizes a proportion of a total number of sample clients having the characteristic to a total number of samples;
constructing a training data set based on the corresponding relation;
calculating an information gain of the feature based on the training dataset;
and constructing a decision tree based on the information gain of each feature.
Optionally, the constructing a training data set based on the correspondence includes:
sequencing the features according to the sequence from the large to the small of the corresponding feature duty ratio to obtain a feature sequence;
selecting the first m-bit features in the feature sequence as target features;
and constructing a training data set based on the corresponding relation among the client risk bearing grade, the target characteristic and the characteristic duty ratio.
Optionally, the calculating, based on the training data set, an information gain of the feature includes:
calculating the information entropy of the client risk tolerance level by utilizing the characteristic duty ratio corresponding to the target characteristic;
and calculating the information gain of the target feature by using the information entropy and a preset conditional entropy.
Optionally, the constructing a decision tree based on the information gain of each feature includes:
and sequencing the target features according to the order of the information gain from large to small to generate a decision tree.
Optionally, the obtaining the feature of the customer to be tested includes:
performing identity verification on the client to be tested by using a face recognition algorithm;
and under the condition that the client to be tested passes the identity verification, acquiring the characteristics of the client to be tested.
Optionally, the recommending the product with the risk bearing grade of the customer greater than the preset grade as the product recommended to the customer to be tested includes:
marking the products purchased by the clients to be tested as target products;
identifying a product with the client risk bearing grade being greater than a preset grade as a first product;
calculating the similarity between the first product and the target product;
and under the condition that the similarity between the first product and the product is larger than a preset threshold value, recommending the first product to the customer to be tested.
A decision tree based product recommendation device, comprising:
the acquisition unit is used for acquiring the characteristics of the client to be tested;
the evaluation unit is used for inputting the characteristics into a decision tree corresponding to each product to obtain the client risk bearing grade of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client is, the stronger the risk bearing capacity of the client to be tested is;
and the recommending unit is used for recommending the products with the risk bearing grades of the clients being larger than the preset grade to the clients to be detected.
A computer readable storage medium comprising a stored program, wherein the program performs the decision tree based product recommendation method.
A decision tree based product recommendation device comprising: a processor, a memory, and a bus; the processor is connected with the memory through the bus;
the memory is used for storing a program, and the processor is used for running the program, wherein the program executes the product recommendation method based on the decision tree when running.
According to the technical scheme, the characteristics of the clients to be tested are obtained, the characteristics are input into the decision trees corresponding to the products aiming at each product, and the client risk bearing grade of each product is obtained, wherein the decision trees are built in advance based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample clients, and the higher the client risk bearing grade is, the stronger the risk bearing capacity of the clients to be tested is. And taking the product with the risk bearing grade of the customer being greater than the preset grade as the product recommended to the customer to be tested. By using the method, based on the pre-constructed decision tree, the client risk bearing grade of each product can be accurately estimated, the products are recommended to the client to be tested according to the client risk bearing grade, and the products recommended to the client to be tested can be ensured to meet the self risk bearing capacity.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a product recommendation method based on a decision tree according to an embodiment of the present application;
FIG. 2 is a schematic diagram of another decision tree-based product recommendation method according to an embodiment of the present application;
fig. 3 is a schematic architecture diagram of a product recommendation device based on a decision tree according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
As shown in fig. 1, a schematic diagram of a product recommendation method based on a decision tree according to an embodiment of the present application includes the following steps:
s101: sample customer information of different kinds of products is obtained in advance.
Among these, the so-called products, for the financial field, include, but are not limited to: funds, stocks, bonds, etc.
S102: and analyzing the sample client information aiming at each product to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client.
Wherein the so-called client risk tolerance level characterizes the risk tolerance capability of the sample client, the higher the client risk tolerance level, the stronger the risk tolerance capability of the sample client.
So-called features, i.e. features of the sample customer, for example features provided in the sample customer purchasing the fund include: the net annual income is more than 15 ten thousand yuan, the age is 20-25 years, the fund purchasing experience is over two years, and no bad credit records are generated.
The feature ratio is a specific weight of the total number of sample clients having features in the total number of samples, specifically, assuming that the total number of samples for purchasing funds is 100, the total number of sample clients having features with annual net income of 15 ten thousand yuan or more is 60 (corresponding feature ratio is 60%), the total number of sample clients having features aged 20 to 25 years is 45 (corresponding feature ratio is 45%), the total number of sample clients having features with fund purchasing experience of two years or more is 30 (corresponding feature ratio is 30%), and the total number of sample clients having features without bad sign records is 95 (corresponding feature ratio is 95%).
S103: and sequencing the features according to the sequence from the large to the small of the corresponding feature duty ratio to obtain a feature sequence.
S104: and selecting the first m-bit features in the feature sequence as target features.
Wherein m is a positive integer.
S105: and constructing a training data set based on the corresponding relation among the client risk bearing grade, the target characteristic and the characteristic duty ratio.
Wherein the training data set includes target features, feature duty ratios corresponding to the target features, and customer risk tolerance levels.
S106: and calculating the information entropy of the client risk tolerance level by utilizing the feature duty ratio corresponding to the target feature.
The specific process of calculating the information entropy of the client risk tolerance level by using the feature ratio corresponding to the target feature is shown in the formula (1).
In formula (1), H (D) represents information entropy, D represents training data set, p i =P(A=a i ),i=1,2,3, n, n is a positive integer, P (a=a i ) Representing the feature duty cycle, a represents the target feature.
S107: and calculating the information gain of the target feature by using the information entropy and the preset conditional entropy.
The specific process of calculating the information gain of the target feature is shown in formula (2) by using the information entropy and the preset conditional entropy.
g(D,A)=H(D)-H(D|A) (2)
In the formula (2), g (D, a) represents the information gain, and H (d|a) represents the conditional entropy.
The so-called conditional entropy H (d|a) is as shown in formula (3).
S108: and sequencing all target features according to the order of the information gain from large to small to generate a decision tree.
S109: and (5) carrying out identity verification on the client to be tested by using a face recognition algorithm.
S110: under the condition that the customer to be tested passes the identity verification, the characteristics of the customer to be tested and the purchased products of the customer to be tested are obtained, and the purchased products of the customer to be tested are identified as target products.
S111: and inputting the characteristics of the clients to be tested into decision trees corresponding to the products aiming at each product to obtain the client risk bearing grade of each product.
S112: and marking the product with the client risk bearing grade larger than the preset grade as a first product.
S113: and calculating the similarity between the first product and the target product.
The specific implementation manner of calculating the similarity between the first product and the target product is known as a person skilled in the art, and will not be described herein.
S114: and under the condition that the similarity between the first product and the target product is larger than a preset threshold value, recommending the first product as the product recommended to the customer to be tested.
In summary, by using the method of the embodiment, based on the pre-constructed decision tree, the risk tolerance level of each product can be accurately estimated, and the product is recommended to the customer to be tested according to the risk tolerance level of the customer, so that the product recommended to the customer to be tested can be ensured to meet the risk tolerance capability of the product.
It should be noted that S101 mentioned in the foregoing embodiment is an optional specific implementation manner of the decision tree-based product recommendation method described in the present application. In addition, S102 mentioned in the foregoing embodiment is also an optional specific implementation manner of the decision tree-based product recommendation method described in the present application. For this reason, the flow mentioned in the above embodiment can be summarized as the method shown in fig. 2.
As shown in fig. 2, a schematic diagram of another product recommendation method based on decision tree according to an embodiment of the present application includes the following steps:
s201: and obtaining the characteristics of the customer to be tested.
S202: and inputting the characteristics into a decision tree corresponding to each product to obtain the customer risk bearing grade of each product.
The decision tree is pre-constructed based on the corresponding relation among the client risk bearing grades, the characteristics and the characteristic duty ratio of the sample client, and the higher the client risk bearing grade is, the stronger the risk bearing capacity of the client to be tested is.
S203: and taking the product with the risk bearing grade of the customer being greater than the preset grade as the product recommended to the customer to be tested.
In summary, by using the method of the embodiment, based on the pre-constructed decision tree, the risk tolerance level of each product can be accurately estimated, and the product is recommended to the customer to be tested according to the risk tolerance level of the customer, so that the product recommended to the customer to be tested can be ensured to meet the risk tolerance capability of the product.
Corresponding to the decision tree-based product recommendation method provided by the embodiment of the application, the embodiment of the application also provides a decision tree-based product recommendation device.
As shown in fig. 3, an architecture diagram of a product recommendation device based on a decision tree according to an embodiment of the present application includes:
an obtaining unit 100 is configured to obtain characteristics of a customer to be tested.
The acquiring unit 100 is specifically configured to: carrying out identity verification on a client to be tested by utilizing a face recognition algorithm; and under the condition that the client to be tested passes the identity verification, acquiring the characteristics of the client to be tested.
The evaluation unit 200 is configured to input, for each product, a feature into a decision tree corresponding to the product, to obtain a customer risk tolerance level of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client, the stronger the risk bearing capacity of the client to be tested.
The evaluation unit 200 is specifically configured to: acquiring sample customer information of a product; analyzing the sample client information to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; wherein the feature duty cycle characterizes the proportion of the total number of sample clients with features in the total number of samples; constructing a training data set based on the corresponding relation; calculating information gain of the feature based on the training dataset; based on the information gain of each feature, a decision tree is constructed.
The process of the evaluation unit 200 for constructing the training data set based on the correspondence relation includes: sequencing all the features according to the sequence from the large to the small of the corresponding feature ratio to obtain a feature sequence; selecting the first m-bit features in the feature sequence as target features; and constructing a training data set based on the corresponding relation among the client risk bearing grade, the target characteristic and the characteristic duty ratio.
The process by which the evaluation unit 200 calculates the information gain of the feature based on the training data set comprises: calculating the information entropy of the client risk bearing grade by utilizing the characteristic duty ratio corresponding to the target characteristic; and calculating the information gain of the target feature by using the information entropy and the preset conditional entropy.
The evaluation unit 200 is configured to construct a decision tree based on the information gain of each feature, and the process includes: and sequencing all target features according to the order of the information gain from large to small to generate a decision tree.
And a recommending unit 300, configured to recommend a product with a risk tolerance level of the customer being greater than a preset level to the customer to be tested.
The recommendation unit 300 specifically is configured to: marking the products purchased by the clients to be tested as target products; the method comprises the steps of marking a product with a customer risk bearing grade greater than a preset grade as a first product; calculating the similarity between the first product and the target product; and under the condition that the similarity between the first products and the products is larger than a preset threshold value, recommending the first products as the products recommended to the clients to be tested.
In summary, by using the method of the embodiment, based on the pre-constructed decision tree, the risk tolerance level of each product can be accurately estimated, and the product is recommended to the customer to be tested according to the risk tolerance level of the customer, so that the product recommended to the customer to be tested can be ensured to meet the risk tolerance capability of the product.
The application also provides a computer readable storage medium, wherein the computer readable storage medium comprises a stored program, and the program executes the product recommendation method based on the decision tree.
The application also provides a product recommendation device based on the decision tree, comprising: a processor, a memory, and a bus. The processor is connected with the memory through a bus, the memory is used for storing a program, and the processor is used for running the program, wherein the product recommendation method based on the decision tree provided by the application is executed when the program runs, and comprises the following steps:
acquiring characteristics of a customer to be tested;
inputting the characteristics into a decision tree corresponding to each product to obtain a customer risk bearing grade of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client is, the stronger the risk bearing capacity of the client to be tested is;
and taking the product with the risk bearing grade of the customer being greater than a preset grade as a product recommended to the customer to be tested.
Optionally, the decision tree is pre-built based on a correspondence between a client risk tolerance level, a feature, and a feature duty ratio of the sample client, and includes:
acquiring sample customer information of the product;
analyzing the sample client information to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; wherein the characteristic duty cycle characterizes a proportion of a total number of sample clients having the characteristic to a total number of samples;
constructing a training data set based on the corresponding relation;
calculating an information gain of the feature based on the training dataset;
and constructing a decision tree based on the information gain of each feature.
Optionally, the constructing a training data set based on the correspondence includes:
sequencing the features according to the sequence from the large to the small of the corresponding feature duty ratio to obtain a feature sequence;
selecting the first m-bit features in the feature sequence as target features;
and constructing a training data set based on the corresponding relation among the client risk bearing grade, the target characteristic and the characteristic duty ratio.
Optionally, the calculating, based on the training data set, an information gain of the feature includes:
calculating the information entropy of the client risk tolerance level by utilizing the characteristic duty ratio corresponding to the target characteristic;
and calculating the information gain of the target feature by using the information entropy and a preset conditional entropy.
Optionally, the constructing a decision tree based on the information gain of each feature includes:
and sequencing the target features according to the order of the information gain from large to small to generate a decision tree.
Optionally, the obtaining the feature of the customer to be tested includes:
performing identity verification on the client to be tested by using a face recognition algorithm;
and under the condition that the client to be tested passes the identity verification, acquiring the characteristics of the client to be tested.
Optionally, the recommending the product with the risk bearing grade of the customer greater than the preset grade as the product recommended to the customer to be tested includes:
marking the products purchased by the clients to be tested as target products;
identifying a product with the client risk bearing grade being greater than a preset grade as a first product;
calculating the similarity between the first product and the target product;
and under the condition that the similarity between the first product and the product is larger than a preset threshold value, recommending the first product to the customer to be tested.
The functions described in the methods of the present application, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computing device readable storage medium. Based on such understanding, a portion of the embodiments of the present application that contributes to the prior art or a portion of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned 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.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A decision tree based product recommendation method, comprising:
acquiring characteristics of a customer to be tested;
inputting the characteristics into a decision tree corresponding to each product to obtain a customer risk bearing grade of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client is, the stronger the risk bearing capacity of the client to be tested is;
marking the products purchased by the clients to be tested as target products;
identifying a product with the client risk bearing grade being greater than a preset grade as a first product;
calculating the similarity between the first product and the target product;
under the condition that the similarity between the first product and the product is larger than a preset threshold, the first product is used as a product recommended to the customer to be tested;
the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client, and comprises the following steps:
acquiring sample customer information of the product;
analyzing the sample client information to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; wherein the characteristic duty cycle characterizes the proportion of the total number of sample clients having the characteristic in the total number of samples, the characteristic including annual net income, age of purchase of funds, and whether there is a bad credit record;
constructing a training data set based on the corresponding relation;
calculating an information gain of the feature based on the training dataset;
and constructing a decision tree based on the information gain of each feature.
2. The method of claim 1, wherein constructing a training dataset based on the correspondence comprises:
sequencing the features according to the sequence from the large to the small of the corresponding feature duty ratio to obtain a feature sequence;
selecting the first m-bit features in the feature sequence as target features;
and constructing a training data set based on the corresponding relation among the client risk bearing grade, the target characteristic and the characteristic duty ratio.
3. The method of claim 2, wherein the calculating the information gain of the feature based on the training dataset comprises:
calculating the information entropy of the client risk tolerance level by utilizing the characteristic duty ratio corresponding to the target characteristic;
and calculating the information gain of the target feature by using the information entropy and a preset conditional entropy.
4. A method according to claim 3, wherein said constructing a decision tree based on the information gain of each of said features comprises:
and sequencing the target features according to the order of the information gain from large to small to generate a decision tree.
5. The method of claim 1, wherein the obtaining the characteristics of the customer under test comprises:
performing identity verification on the client to be tested by using a face recognition algorithm;
and under the condition that the client to be tested passes the identity verification, acquiring the characteristics of the client to be tested.
6. A decision tree based product recommendation device, comprising:
the acquisition unit is used for acquiring the characteristics of the client to be tested;
the evaluation unit is used for inputting the characteristics into a decision tree corresponding to each product to obtain the client risk bearing grade of each product; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; the higher the risk bearing grade of the client is, the stronger the risk bearing capacity of the client to be tested is; the decision tree is pre-constructed based on the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client, and comprises the following steps: acquiring sample customer information of the product; analyzing the sample client information to obtain the corresponding relation among the client risk bearing grade, the characteristics and the characteristic duty ratio of the sample client; wherein the characteristic duty cycle characterizes the proportion of the total number of sample clients having the characteristic in the total number of samples, the characteristic including annual net income, age of purchase of funds, and whether there is a bad credit record; constructing a training data set based on the corresponding relation; calculating an information gain of the feature based on the training dataset; constructing a decision tree based on the information gain of each feature;
the recommending unit is used for recommending the products with the risk bearing grades of the clients being larger than a preset grade to the clients to be detected;
the recommending unit is specifically configured to identify a product purchased by the customer to be tested as a target product; identifying a product with the client risk bearing grade being greater than a preset grade as a first product; calculating the similarity between the first product and the target product; and under the condition that the similarity between the first product and the product is larger than a preset threshold value, recommending the first product to the customer to be tested.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program performs the decision tree based product recommendation method of any of claims 1-5.
8. A decision tree based product recommendation device, comprising: a processor, a memory, and a bus; the processor is connected with the memory through the bus;
the memory is used for storing a program, and the processor is used for running the program, wherein the program runs to execute the decision tree-based product recommendation method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110486328.9A CN113052689B (en) | 2021-04-30 | 2021-04-30 | Product recommendation method and device based on decision tree |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110486328.9A CN113052689B (en) | 2021-04-30 | 2021-04-30 | Product recommendation method and device based on decision tree |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113052689A CN113052689A (en) | 2021-06-29 |
CN113052689B true CN113052689B (en) | 2024-03-26 |
Family
ID=76518131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110486328.9A Active CN113052689B (en) | 2021-04-30 | 2021-04-30 | Product recommendation method and device based on decision tree |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113052689B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109102159A (en) * | 2018-07-18 | 2018-12-28 | 平安科技(深圳)有限公司 | Passenger's rating model generation method, device, computer equipment and storage medium |
CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技(深圳)有限公司 | Financial product recommended method, device, computer equipment and storage medium |
CN109670962A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Finance product method for pushing, device, equipment and storage medium based on big data |
WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技(深圳)有限公司 | Information pushing method and device, computer device and storage medium |
CN111259922A (en) * | 2019-12-25 | 2020-06-09 | 江苏艾佳家居用品有限公司 | Order data processing method and device based on customer order-returning early warning |
CN111695938A (en) * | 2020-06-05 | 2020-09-22 | 中国工商银行股份有限公司 | Product pushing method and system |
CN112329843A (en) * | 2020-11-03 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Call data processing method, device, equipment and storage medium based on decision tree |
-
2021
- 2021-04-30 CN CN202110486328.9A patent/CN113052689B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技(深圳)有限公司 | Information pushing method and device, computer device and storage medium |
CN109102159A (en) * | 2018-07-18 | 2018-12-28 | 平安科技(深圳)有限公司 | Passenger's rating model generation method, device, computer equipment and storage medium |
CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技(深圳)有限公司 | Financial product recommended method, device, computer equipment and storage medium |
CN109670962A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Finance product method for pushing, device, equipment and storage medium based on big data |
CN111259922A (en) * | 2019-12-25 | 2020-06-09 | 江苏艾佳家居用品有限公司 | Order data processing method and device based on customer order-returning early warning |
CN111695938A (en) * | 2020-06-05 | 2020-09-22 | 中国工商银行股份有限公司 | Product pushing method and system |
CN112329843A (en) * | 2020-11-03 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Call data processing method, device, equipment and storage medium based on decision tree |
Also Published As
Publication number | Publication date |
---|---|
CN113052689A (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10572885B1 (en) | Training method, apparatus for loan fraud detection model and computer device | |
CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
CN107103171B (en) | Modeling method and device of machine learning model | |
CN106600369A (en) | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification | |
US20140351109A1 (en) | Method and apparatus for automatically identifying a fraudulent order | |
US20170286962A1 (en) | Bulk Dispute Challenge System | |
CN112102073A (en) | Credit risk control method and system, electronic device and readable storage medium | |
Suryanarayana et al. | Machine learning approaches for credit card fraud detection | |
CN110991474A (en) | Machine learning modeling platform | |
CN111260189B (en) | Risk control method, risk control device, computer system and readable storage medium | |
CN113177839A (en) | Credit risk assessment method, device, storage medium and equipment | |
CN111695938B (en) | Product pushing method and system | |
CN116485406A (en) | Account detection method and device, storage medium and electronic equipment | |
CN106372964A (en) | Behavior loyalty identification and management method, system and terminal | |
US20220261926A1 (en) | Method and system for credit card holder identification | |
CN114782201A (en) | Stock recommendation method and device, computer equipment and storage medium | |
CN114399367A (en) | Insurance product recommendation method, device, equipment and storage medium | |
CN116596576B (en) | Target recommendation method and device | |
CN112330373A (en) | User behavior analysis method and device and computer readable storage medium | |
CN112966728A (en) | Transaction monitoring method and device | |
CN113052689B (en) | Product recommendation method and device based on decision tree | |
CN113177733B (en) | Middle and small micro enterprise data modeling method and system based on convolutional neural network | |
CN115375494A (en) | Financial product recommendation method, device, storage medium and equipment | |
CN110570301B (en) | Risk identification method, device, equipment and medium | |
CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |