CN111768110A - E-commerce platform customer value evaluation method and system based on random forest algorithm - Google Patents
E-commerce platform customer value evaluation method and system based on random forest algorithm Download PDFInfo
- Publication number
- CN111768110A CN111768110A CN202010627903.8A CN202010627903A CN111768110A CN 111768110 A CN111768110 A CN 111768110A CN 202010627903 A CN202010627903 A CN 202010627903A CN 111768110 A CN111768110 A CN 111768110A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- random forest
- commerce platform
- customer
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F18/24—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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a random forest algorithm-based e-commerce platform customer value evaluation method and system, wherein evaluation indexes influencing customer value evaluation are selected from an e-commerce platform database; cleaning and sorting the selected evaluation index data; extracting client value evaluation samples from the cleaned and sorted evaluation index data, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples; training a random forest model according to the training sample by taking the evaluation indexes after cleaning and sorting as features; inputting the test sample into a random forest model, and when the accuracy of an output value is greater than a set threshold value, determining the random forest model as a final customer value evaluation model of the e-commerce platform; and evaluating the customer value of the e-commerce platform by using the customer value evaluation model of the e-commerce platform. The method and the system can evaluate the value of the customer for the e-commerce platform, are favorable for providing marketing decision support according to the evaluation result, and improve the loyalty of the customer in a targeted manner.
Description
Technical Field
The invention belongs to the field of e-commerce platform customer value evaluation, and particularly relates to an e-commerce platform customer value evaluation method and system based on a random forest algorithm.
Background
With the social and economic development entering a new normal state, rural electric power companies become emerging markets which are greatly supported by the current countries, and more consumers purchase agricultural products through rural electric power company platforms. In the face of tens of thousands of consumers and intense market competition, high-quality value customers of rural e-commerce platforms have a greater risk of loss. Therefore, value evaluation is carried out on the customers, value grade division is realized, and the customer loyalty is improved in a targeted manner, so that the method becomes a major problem for rural power merchants.
In the past, enterprise managers made decisions through intuition and experience, rather than building on quantitative analysis of problems on a scientific basis. However, the external environment faced by enterprise managers is changed rapidly nowadays, the environment of the e-commerce is more complex than the previous environment, and the complexity is increased day by day, so that it is difficult to accurately and timely propose a scientific decision scheme only by the subjective judgment of a decision maker.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides the e-commerce platform customer value evaluation method and system based on the random forest algorithm, which can evaluate the customer value of the e-commerce platform, further contribute to providing marketing decision support according to the evaluation result and purposefully improve customer loyalty.
In order to solve the technical problems, the invention is realized by the following technical scheme:
a customer value evaluation method of an E-commerce platform based on a random forest algorithm comprises the following steps:
step 1: selecting evaluation indexes influencing the value evaluation of the customer from an e-commerce platform database;
step 2: cleaning and sorting the evaluation index data selected in the step 1;
and step 3: extracting client value evaluation samples from the evaluation index data cleaned and sorted in the step 2, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
and 4, step 4: training a random forest model according to the training samples in the step 3 by taking the evaluation indexes cleaned and sorted in the step 2 as features;
and 5: inputting the test sample in the step 3 into the random forest model in the step 4, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final customer value evaluation model of the e-commerce platform;
step 6: and (5) evaluating the customer value of the e-commerce platform by using the e-commerce platform customer value evaluation model obtained in the step 5.
Further, in step 1, the evaluation indexes include single frequency in a single month, average consumption amount in a single month, number of times of repurchase of a single month commodity and latest purchasing time.
Further, in step 2, the cleaning of the evaluation index data specifically comprises: satisfying the demand of random forest algorithm, but having missing evaluation index data, and filling up missing values by a filling-up algorithm; deleting evaluation index data which are missing and can not meet the requirements of the random forest algorithm;
the evaluation index data arrangement specifically comprises the following steps: calculating a standard deviation of the data corresponding to each evaluation index, and:
recording the data smaller than the standard deviation of single frequency in a single month as low, otherwise recording the data as high;
the data smaller than the standard deviation of the average consumption amount in a single month is recorded as low, otherwise, the data is recorded as high;
the data which is less than the standard deviation of the number of times of the single-month commodity repurchase is recorded as low, otherwise, the data is recorded as high;
data less than the standard deviation of the most recent purchase is recorded as near, and vice versa as far.
Further, the e-commerce platform customer value levels include: when the single frequency of the customer in a single month is high, the average consumption amount in the single month is high, the repeated purchasing times of the single-month commodities are high, and the latest purchasing time is short, the three-level condition is established; when the single frequency of the customer in a single month is low, the average consumption amount in the single month is low, the repeated purchase times of the single-month commodities are low, and the last purchase time is long, the customer is in the first level; the other case is two-stage.
Further, in step 4, data samples are randomly selected, characteristics are randomly selected, and a plurality of decision trees are built to form a random forest model.
Further, in step 5, when the accuracy of the output value is smaller than the set threshold, adjusting the evaluation index and the number of training samples, and adjusting the random forest model until the accuracy of the output value is larger than the set threshold.
Further, the influence of each evaluation index on the heterogeneity of the observed values on each node of the classification tree is calculated through the kini index, so that the importance of the evaluation indexes is compared, and the evaluation indexes are adjusted according to the importance.
A customer value evaluation system of an E-commerce platform based on a random forest algorithm comprises:
the selection module is used for selecting evaluation indexes influencing the value evaluation of the customer from the e-commerce platform database;
the cleaning and sorting module is used for cleaning and sorting the evaluation index data selected by the selection module;
the client value evaluation sample extraction module is used for extracting client value evaluation samples from the evaluation index data cleaned and sorted by the cleaning and sorting module, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
the random forest model training module is used for training a random forest model according to training samples defined by the customer value evaluation sample extraction module by taking the evaluation indexes cleaned and sorted by the cleaning and sorting module as characteristics;
the judgment module is used for inputting the test samples defined by the customer value evaluation sample extraction module into a random forest model obtained by training of the random forest model training module, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final customer value evaluation model of the e-commerce platform;
and the evaluation module is used for evaluating the customer value of the e-commerce platform by using the e-commerce platform customer value evaluation model obtained by judgment of the judgment module.
Compared with the prior art, the invention has at least the following beneficial effects: the invention relates to an e-commerce platform customer value evaluation method based on a random forest algorithm, which comprises the steps of selecting evaluation indexes influencing customer value evaluation from an e-commerce platform database; cleaning and sorting the selected evaluation index data; extracting client value evaluation samples from the cleaned and sorted evaluation index data, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples; training a random forest model according to the training sample by taking the evaluation indexes after cleaning and sorting as features; inputting the test sample into a random forest model, and when the accuracy of an output value is greater than a set threshold value, determining the random forest model as a final customer value evaluation model of the e-commerce platform; and evaluating the customer value of the e-commerce platform by using the customer value evaluation model of the e-commerce platform. The method comprises the steps of using data in a rural e-commerce platform database as a sample, selecting a plurality of important evaluation indexes, and constructing a rural e-commerce platform customer value evaluation model based on random forest algorithm autonomous learning; the rural e-commerce platform customer value evaluation model provides marketing decision support for the rural e-commerce platform to evaluate the customer value, customer loyalty is improved pertinently, the rural e-commerce platform customer value evaluation model is not affected by subjectivity, and accuracy is high.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a model training and construction process;
FIG. 3 is a decision tree model trained.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As a specific implementation mode of the invention, the method for evaluating the customer value of the rural e-commerce platform based on the random forest algorithm comprises the following steps:
step 1: selecting evaluation indexes influencing the value evaluation of customers from a rural e-commerce platform database, wherein the evaluation indexes comprise single frequency under a single month, average consumption amount of the single month, repeated purchasing times of single month commodities and latest purchasing time;
the selection of the evaluation indexes follows the following principle:
firstly, an effectiveness principle: namely, the selected evaluation index is effective and can represent the customer value of the rural e-commerce platform; II, importance principle: namely, the selected evaluation indexes have strong relevance with the client value of the rural e-commerce platform;
step 2: cleaning and sorting the evaluation index data selected in the step 1;
the evaluation index data cleaning specifically comprises the following steps: satisfying the demand of random forest algorithm, but having missing evaluation index data, and filling up missing values by a filling-up algorithm; deleting evaluation index data which are missing and can not meet the requirements of the random forest algorithm;
the evaluation index data arrangement specifically comprises the following steps: calculating a standard deviation of the data corresponding to each evaluation index, and:
recording the data smaller than the standard deviation of single frequency in a single month as low, otherwise recording the data as high;
the data smaller than the standard deviation of the average consumption amount in a single month is recorded as low, otherwise, the data is recorded as high;
the data which is less than the standard deviation of the number of times of the single-month commodity repurchase is recorded as low, otherwise, the data is recorded as high;
recording the data smaller than the standard deviation of the latest purchasing time as near data, and otherwise, recording the data as far data;
and step 3: extracting client value evaluation samples from the evaluation index data cleaned and sorted in the step 2, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
the customer value grades of the rural e-commerce platform comprise: when the single frequency of the customer in a single month is high, the average consumption amount in the single month is high, the repeated purchasing times of the single-month commodities are high, and the latest purchasing time is short, the three-level condition is established; when the single frequency of the customer in a single month is low, the average consumption amount in the single month is low, the repeated purchase times of the single-month commodities are low, and the last purchase time is long, the customer is in the first level; the other cases are two stages; specifically, as shown in table one:
takew-rural e-commerce platform customer value grade evaluation rule
The extracted rural e-commerce customer value evaluation sample is shown in table two:
meter II rural e-commerce customer value evaluation sample
And 4, step 4: taking the evaluation indexes cleaned and sorted in the step 2 as features, and training a decision tree model according to the training samples in the step 3;
randomly selecting data samples, randomly selecting characteristics, and establishing a plurality of decision trees to form a random forest model; wherein a decision tree model is trained as shown in FIG. 3;
and 5: inputting the test sample in the step 3 into the random forest model in the step 4, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final rural power provider platform customer value evaluation model;
when the accuracy of the output value is smaller than a set threshold, adjusting the evaluation index and the number of training samples, and adjusting the random forest model until the accuracy of the output value is larger than the set threshold;
the specific process of constructing the client value evaluation model of the rural power business platform is shown in fig. 2, wherein the process of training the model is a well-known technology and is not described in detail herein; the accuracy rate is determined according to the actual situation, and the factors influencing the accuracy rate mainly comprise two points, namely an evaluation index and the number of training samples;
and calculating the influence of each evaluation index on the heterogeneity of the observed value on each node of the classification tree through the Gini index, thereby comparing the importance of the evaluation indexes and adjusting the evaluation indexes according to the importance.
As shown in fig. 3, in a decision tree model trained, the calculated kini index of each evaluation index is: the single frequency of the single month is 0.34, the average consumption amount of the single month is 0.40, the repeated purchasing times of the single month commodities are 0.53, and the latest purchasing time is 0.64; the smaller the Kini index is, the better the evaluation index is;
step 6: and (5) evaluating the client value of the rural e-commerce platform by using the client value evaluation model of the rural e-commerce platform obtained in the step (5).
The method comprises the steps of using data in a rural e-commerce platform database as a sample, selecting a plurality of evaluation indexes, and constructing a rural e-commerce platform customer value evaluation model based on random forest algorithm autonomous learning; the model is used for evaluating the customer value of a rural e-commerce platform, providing marketing decision support and improving customer loyalty in a targeted manner. The model is not affected by subjectivity and has high accuracy.
The invention relates to a rural e-commerce platform customer value evaluation system based on a random forest algorithm, which comprises the following steps:
the selection module is used for selecting evaluation indexes influencing the evaluation of the customer value from the rural e-commerce platform database;
the cleaning and sorting module is used for cleaning and sorting the evaluation index data selected by the selection module;
the client value evaluation sample extraction module is used for extracting client value evaluation samples from the evaluation index data cleaned and sorted by the cleaning and sorting module, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
the random forest model training module is used for training a random forest model according to training samples defined by the customer value evaluation sample extraction module by taking the evaluation indexes cleaned and sorted by the cleaning and sorting module as characteristics;
the judgment module is used for inputting the test samples defined by the customer value evaluation sample extraction module into a random forest model obtained by training of the random forest model training module, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final customer value evaluation model of the rural e-commerce platform;
and the evaluation module is used for evaluating the client value of the rural e-commerce platform by utilizing the rural e-commerce platform client value evaluation model obtained by judgment of the judgment module.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A customer value evaluation method of an E-commerce platform based on a random forest algorithm is characterized by comprising the following steps:
step 1: selecting evaluation indexes influencing the value evaluation of the customer from an e-commerce platform database;
step 2: cleaning and sorting the evaluation index data selected in the step 1;
and step 3: extracting client value evaluation samples from the evaluation index data cleaned and sorted in the step 2, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
and 4, step 4: training a random forest model according to the training samples in the step 3 by taking the evaluation indexes cleaned and sorted in the step 2 as features;
and 5: inputting the test sample in the step 3 into the random forest model in the step 4, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final customer value evaluation model of the e-commerce platform;
step 6: and (5) evaluating the customer value of the e-commerce platform by using the e-commerce platform customer value evaluation model obtained in the step 5.
2. The method for evaluating the customer value of the e-commerce platform based on the random forest algorithm as claimed in claim 1, wherein in the step 1, the evaluation indexes comprise single frequency in a single month, average consumption amount in the single month, repeated purchase times of commodities in the single month and latest purchase time.
3. The e-commerce platform customer value evaluation method based on the random forest algorithm as claimed in claim 2, wherein in the step 2, the evaluation index data cleaning specifically comprises the following steps: satisfying the demand of random forest algorithm, but having missing evaluation index data, and filling up missing values by a filling-up algorithm; deleting evaluation index data which are missing and can not meet the requirements of the random forest algorithm;
the evaluation index data arrangement specifically comprises the following steps: calculating a standard deviation of the data corresponding to each evaluation index, and:
recording the data smaller than the standard deviation of single frequency in a single month as low, otherwise recording the data as high;
the data smaller than the standard deviation of the average trading amount in a single month is recorded as low, otherwise, the data is recorded as high;
the data which is less than the standard deviation of the number of times of the single-month commodity repurchase is recorded as low, otherwise, the data is recorded as high;
data less than the standard deviation of the most recent purchase is recorded as near, and vice versa as far.
4. The e-commerce platform customer value evaluation method based on the random forest algorithm as claimed in claim 3, wherein the e-commerce platform customer value rating comprises: when the single frequency of the customer in a single month is high, the average consumption amount in the single month is high, the repeated purchasing times of the single-month commodities are high, and the latest purchasing time is short, the three-level condition is established; when the single-month purchase frequency of a customer is low, the average single-month transaction amount is low, the single-month commodity re-purchase frequency is low and the last purchase time is long, the customer is in the first level; the other case is two-stage.
5. The method for evaluating the customer value of the E-commerce platform based on the random forest algorithm as claimed in claim 1, wherein in the step 4, data samples are selected randomly, characteristics are selected randomly, and a plurality of decision trees are built to form a random forest model.
6. The method for evaluating the customer value of the E-commerce platform based on the random forest algorithm as claimed in claim 1, wherein in the step 5, when the accuracy of the output value is smaller than a set threshold, the evaluation index and the number of training samples are adjusted, and the random forest model is adjusted until the accuracy of the output value is larger than the set threshold.
7. The e-commerce platform customer value evaluation method based on the random forest algorithm as claimed in claim 6, wherein the influence of each evaluation index on the heterogeneity of the observed values on each node of the classification tree is calculated through a kini index, so that the importance of the evaluation indexes is compared, and the evaluation indexes are adjusted according to the importance.
8. A customer value evaluation system of an E-commerce platform based on a random forest algorithm is characterized by comprising the following steps:
the selection module is used for selecting evaluation indexes influencing the value evaluation of the customer from the e-commerce platform database;
the cleaning and sorting module is used for cleaning and sorting the evaluation index data selected by the selection module;
the client value evaluation sample extraction module is used for extracting client value evaluation samples from the evaluation index data cleaned and sorted by the cleaning and sorting module, wherein part of the client value evaluation samples are used as training samples, and the rest of the client value evaluation samples are used as test samples;
the random forest model training module is used for training a random forest model according to training samples defined by the customer value evaluation sample extraction module by taking the evaluation indexes cleaned and sorted by the cleaning and sorting module as characteristics;
the judgment module is used for inputting the test samples defined by the customer value evaluation sample extraction module into a random forest model obtained by training of the random forest model training module, and when the accuracy of the output value is greater than a set threshold value, the random forest model is a final customer value evaluation model of the e-commerce platform;
and the evaluation module is used for evaluating the customer value of the e-commerce platform by using the e-commerce platform customer value evaluation model obtained by judgment of the judgment module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010627903.8A CN111768110A (en) | 2020-07-02 | 2020-07-02 | E-commerce platform customer value evaluation method and system based on random forest algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010627903.8A CN111768110A (en) | 2020-07-02 | 2020-07-02 | E-commerce platform customer value evaluation method and system based on random forest algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111768110A true CN111768110A (en) | 2020-10-13 |
Family
ID=72723366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010627903.8A Pending CN111768110A (en) | 2020-07-02 | 2020-07-02 | E-commerce platform customer value evaluation method and system based on random forest algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111768110A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990386A (en) * | 2021-05-17 | 2021-06-18 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN115423049A (en) * | 2022-11-03 | 2022-12-02 | 荣耀终端有限公司 | Value evaluation model training method, value evaluation method and electronic equipment |
-
2020
- 2020-07-02 CN CN202010627903.8A patent/CN111768110A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990386A (en) * | 2021-05-17 | 2021-06-18 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN112990386B (en) * | 2021-05-17 | 2021-08-03 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN115423049A (en) * | 2022-11-03 | 2022-12-02 | 荣耀终端有限公司 | Value evaluation model training method, value evaluation method and electronic equipment |
| CN115423049B (en) * | 2022-11-03 | 2023-09-12 | 荣耀终端有限公司 | Training method of value evaluation model, value evaluation method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826886A (en) | Electric power customer portrait construction method based on clustering algorithm and principal component analysis | |
| CN107563645A (en) | A kind of Financial Risk Analysis method based on big data | |
| CN111768110A (en) | E-commerce platform customer value evaluation method and system based on random forest algorithm | |
| CN111583012B (en) | Method for evaluating default risk of credit, debt and debt main body by fusing text information | |
| CN107609771A (en) | A kind of supplier's value assessment method | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN108364191A (en) | Top-tier customer Optimum Identification Method and device based on random forest and logistic regression | |
| CN112561339A (en) | High-quality customer identification method | |
| CN109711424A (en) | A kind of rule of conduct acquisition methods, device and equipment based on decision tree | |
| CN112948667A (en) | Supplier recommendation system and method based on bidding | |
| CN110458576A (en) | The network trading that detects is counter in a kind of fusion ex ante forecasting and thing cheats method | |
| Baum et al. | R&D expenditures and geographical sales diversification | |
| CN116128627A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN113988459A (en) | Small and medium-sized enterprise growth assessment method and system based on electric power marketing data | |
| CN113450004A (en) | Power credit report generation method and device, electronic equipment and readable storage medium | |
| CN117114812A (en) | Financial product recommendation method and device for enterprises | |
| CN116883153A (en) | Pedestrian credit investigation-based automobile finance pre-credit rating card development method and terminal | |
| CN111160947A (en) | Intelligent system for automobile part sales prediction | |
| CN115393098A (en) | Financing product information recommendation method and device | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| CN109754281B (en) | Supplier loss prediction method | |
| CN113269412A (en) | Risk assessment method and related device | |
| Petrovska et al. | Forecasting Macedonian Inflation: Evaluation of different models for short-term forecasting | |
| Gu et al. | Research on retailer churn prediction based on spatial-temporal features | |
| CN107844921A (en) | A kind of customer action predictor method based on embedding technologies |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201013 |