CN112561339A - High-quality customer identification method - Google Patents

High-quality customer identification method Download PDF

Info

Publication number
CN112561339A
CN112561339A CN202011499872.9A CN202011499872A CN112561339A CN 112561339 A CN112561339 A CN 112561339A CN 202011499872 A CN202011499872 A CN 202011499872A CN 112561339 A CN112561339 A CN 112561339A
Authority
CN
China
Prior art keywords
client
customer
quality
value
identification
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.)
Withdrawn
Application number
CN202011499872.9A
Other languages
Chinese (zh)
Inventor
冷勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiangyun Zhihui Technology Co ltd
Original Assignee
Beijing Xiangyun Zhihui Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Xiangyun Zhihui Technology Co ltd filed Critical Beijing Xiangyun Zhihui Technology Co ltd
Priority to CN202011499872.9A priority Critical patent/CN112561339A/en
Publication of CN112561339A publication Critical patent/CN112561339A/en
Withdrawn legal-status Critical Current

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
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention provides a high-quality client identification method, which comprises the following steps: uniformly formatting data to present highlighted data, and balancing the highlighted data; constructing an index system by utilizing four main dimensions of credit degree, economic value, development potential and client stability, and fusing the index system together according to machine learning so as to establish a comprehensive evaluation model of client value; constructing a judgment matrix of the identification index, processing data by using a square root method, and constructing a high-quality identification client model through machine learning; the method effectively and comprehensively evaluates the target customers, quickly and accurately identifies the target customers, has low investment and marketing cost and high customer return cost, and thus improves the overall economic benefit of enterprises.

Description

High-quality customer identification method
Technical Field
The invention belongs to the technical field of data analysis, and particularly relates to a high-quality client identification method.
Background
With the deep advance of national electric power market reformation, the market of the electricity selling side is gradually released, the competition of the electricity selling market is gradually intensified, and high-quality customers become an important competitive focus. The method has the advantages that high-quality customers are excavated, accurate and differentiated customer service is realized, customer service satisfaction is improved, and the method becomes an important cause. At present, in the power industry, a plurality of clients are rated according to the judgment of electric quantity and electric charge, or a simple analytic hierarchy process model is used for identification, and the like, the existing capacity of the clients is mainly considered, but the capacity of the target clients cannot be comprehensively evaluated, so that the identification result error of high-quality clients is large, and the overall economic benefit of power enterprises is influenced.
Disclosure of Invention
The invention aims to provide a high-quality client identification method, and aims to solve the problem that the capacity of a target client cannot be comprehensively evaluated, so that the identification result of a high-quality client has a large error.
In order to achieve the purpose, the invention adopts the technical scheme that: a high-quality customer identification method is provided, which comprises the following steps:
step 1: uniformly formatting data to present highlighted data, and balancing the highlighted data;
step 2: constructing an index system by utilizing four main dimensions of credit degree, economic value, development potential and client stability, and fusing the index system together according to machine learning so as to establish a comprehensive evaluation model of client value;
and step 3: constructing a judgment matrix of the identification index, processing data by using a square root method, and constructing a high-quality identification client model through machine learning;
and 4, step 4: and arranging according to the client value evaluation result in a descending order, and identifying by using the high-quality client model.
Preferably, the method for deriving the comprehensive evaluation model of the customer value in step 2 includes:
step 201: the initial credit score is Z, the normal transaction times and default times of the client in the account opening period determine the credit rating, and the client credit score formula is constructed as follows:
Figure DEST_PATH_IMAGE001
wherein z is an initial credit point, eta is a calculation coefficient, n represents the normal transaction times of the customer, and x represents the default transaction times of the customer;
step 202: constructing a customer purchasing ability formula according to the single purchasing amount M and the purchasing frequency N of the customer:
Figure 348977DEST_PATH_IMAGE002
wherein R is the profit margin of the client i for purchasing the product, S is the premium rate paid by the enterprise for the client i, TCO represents the total cost of ownership of the client i, and X and Y are the product purchase conversion frequency and the urgent order modification frequency of the client i respectively;
step 203: establishing a calculation expression of the total term of cooperation with the client according to the intention of cooperation between the client and the enterprise:
Figure DEST_PATH_IMAGE003
wherein the parameter PcRepresenting the disturbance probability of the client, i is the client;
step 204, profit brought by the possibility that the client purchases enterprise products in the future period is built, and an evaluation formula of the potential value of the client is constructed as follows:
Figure 402865DEST_PATH_IMAGE004
wherein, PB isijProbability, PF, of choosing a product or service j for a customer i to purchaseijAnd PVijThe profits and the consumption cost brought to the enterprises after the products or the services j are selected for the client i respectively are obtained, and the PF is obtainedij-PVijThe value of (a) is net profit;
step 205: and integrating the client evaluation indexes, and fusing the credit, economic value, development potential and client stability to construct a comprehensive evaluation model of the client value:
Figure DEST_PATH_IMAGE005
where score is the client credit score, E (i) is the client attitude, VPiFor potential value of the customer, PiCapabilities are purchased for the customer.
Preferably, in said step 203, P is used when the customer relationship is in the preliminary stagecIs 0.9 and gradually decreases, when the relationship between the client and the enterprise is a cooperative relationship, P is the value ofcIs 0.1.
Preferably, the machine-learned indexes in step 3 include a client external environment condition, a client financial condition, a client demand condition, and a client growth.
Preferably, the external environmental condition ratio of the client is 15.86%; the client financial condition ratio is 22.13%; the customer demand condition ratio is 31.74 percent; the customer growth ratio percentage was 30.3%.
Preferably, the step 4 reuses the high-quality customer model for identification according to the top 5% of the customer evaluation value.
Preferably, the data balance processing method in step 1 is to keep the client data balanced by adjusting the class weight value, the probability estimation value of the adjustment node, and the decision threshold according to different sampling modes.
The high-quality client identification method provided by the invention has the beneficial effects that: compared with the prior art, the invention discloses a high-quality client identification method, which comprises the following steps: carrying out format unified processing on the data, and carrying out balanced processing on the data if the data has an unbalanced phenomenon; constructing an index system from four main dimensions of credit, economic value, development potential and customer stability, establishing a plurality of corresponding sub-dimension indexes under each dimension, training an integration strategy for the classifier to obtain a strong classifier, fusing the strong classifier together by using a machine learning algorithm, and establishing a comprehensive evaluation model of the customer value; establishing a judgment matrix of the identification indexes, processing data by using a square root method, and establishing index weight of a high-quality identification client model through machine learning; the method can effectively carry out comprehensive evaluation on the target customers, quickly and accurately identify the target customers, has low investment and marketing cost and high customer return cost, and thus improves the overall economic benefit of enterprises.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is an evaluation structure of a machine learning algorithm according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the development of a premium customer relationship according to an embodiment of the present invention;
FIG. 3 is a partial identification index and a weight calculation result thereof according to an embodiment of the present invention;
fig. 4 is a flowchart of a high-quality client identification method according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 and 4 together, a description will now be given of a high-quality customer identification method according to the present invention. The high-quality client identification method comprises the following steps:
s1: and uniformly formatting the data to generate the highlighted data, and balancing the highlighted data.
Specifically, when a related client transacts with an enterprise, related enterprise or personal information needs to be filled in, so that data acquisition is realized, the data is subjected to format unified processing, and when a type of data sample with a unified format is found to be far larger than another data sample, the data is unbalanced. And dividing the sampling mode into over-sampling and under-sampling according to different sampling modes, and balancing the client data by adjusting the weight value of the class, adjusting the probability evaluation value of the node and adjusting the decision threshold.
S2: an index system is constructed by utilizing four main dimensions of credit degree, economic value, development potential and customer stability, and is fused together according to machine learning, so that a comprehensive evaluation model of customer value is established.
Specifically, an index system is constructed by utilizing four main dimensions of credit, economic value, development potential and customer stability, a machine learning algorithm is used for evaluating a structure, as shown in fig. 1, a training set trains each classifier, each classifier is fused to establish a comprehensive flat model of customer value, and a derivation method of the comprehensive evaluation model of customer value comprises the following steps:
in this embodiment, S201 is Z, the initial credit score is Z, the number of normal transactions and the number of default times of the customer during the account opening period determine the credit rating, and the customer credit score formula is constructed as follows:
Figure DEST_PATH_IMAGE007
wherein z is the initial credit score, η is the calculation coefficient, n represents the number of normal transactions of the customer, and x represents the number of default transactions of the customer.
Specifically, the initial credit integral is set to be 90 points, as the account opening time increases, the credit rating result of the customer changes as the customer continuously conducts transactions during the account opening period, if the normal transaction times of the customer are greater than the default transaction times, the credit rating of the customer increases, otherwise, the credit rating of the customer decreases, when the credit rating of the customer is [95, 100], the credit rating of the corresponding customer is level i, and if the credit rating is in the interval [80, 95], the credit rating is level ii, and other ratings are level iii.
In this embodiment, S202 constructs a customer purchasing power formula according to the customer single purchase amount M and the purchasing frequency N:
Figure 75155DEST_PATH_IMAGE008
wherein R is the profit margin of the customer i for purchasing the product, S is the premium rate paid by the enterprise for the customer i, TCO represents the total cost of ownership of the customer i, and X and Y are the product purchase conversion frequency and the urgent order modification frequency of the customer i, respectively.
In this embodiment, in S203, a calculation expression of the total term of cooperation with the client is established according to the intention of cooperation between the client and the enterprise:
Figure DEST_PATH_IMAGE009
wherein the parameter PcRepresenting the disturbance probability of the client, i is the client;
specifically, the parameter PcRepresenting the disturbance probability of the client, influenced by various factors such as financial conditions of other enterprises and clients, PcThe value of (A) will change, in order to ensure the maintenance of the high-quality customer relationship, a corresponding relationship development scheme needs to be formulated, such as the customer relationship development flow shown in fig. 2, the customer management is divided into a high-quality customer inoculation stage, a high-quality customer primary stage, a high-quality customer middle stage, a collaborative high-quality customer management stage and an intermittent high-quality customer management stage, when the customer relationship is in the primary stage, P iscIs 0.9 and gradually decreases, when the relationship between the client and the enterprise is a cooperative relationship, P is the value ofcThe value of (a) is 0.1, so that the relationship with the client can be better maintained.
In this embodiment, in S204, the client may purchase profits brought by enterprise products in the future, and the evaluation formula for constructing the potential value of the client is as follows:
Figure 635449DEST_PATH_IMAGE010
wherein, PB isijProbability, PF, of choosing a product or service j for a customer i to purchaseijAnd PVijThe profits and the consumption cost brought to the enterprises after the products or the services j are selected for the client i respectively are obtained, and the PF is obtainedij-PVijThe value of (d) is net profit.
In this embodiment, S205 integrates the above customer evaluation indexes, and integrates the credit, economic value, development potential, and customer stability to construct a comprehensive evaluation model of the customer value:
Figure DEST_PATH_IMAGE011
where score is the client credit score, E (i) is the client attitude, VPiFor potential value of the customer, PiCapabilities are purchased for the customer.
S3: and (3) constructing a judgment matrix of the identification index, processing data by using a square root method, and constructing a high-quality identification client model through machine learning.
In this embodiment, as shown in fig. 3, the machine learning index includes a client external environment condition, a client financial condition, a client demand condition, and a client growth rate, the client external environment condition ratio is 15.86%, the client financial condition ratio is 22.13%, the client demand condition ratio is 31.74%, and the client growth rate ratio is 30.3%.
S4: and arranging according to the client value evaluation result in a descending order, and identifying by using the high-quality client model.
In the embodiment, the high-quality client model is identified according to the client evaluation value of 5%, so that the cost of marketing investors is reduced, the identification of target clients is accelerated, the client return cost is high, and the overall economic benefit of enterprises is improved.
The following are exemplary: performing high-quality client identification on the database, wherein the experimental time is 5 months in 2020, and the total number of sampled users to be identified is 10, wherein 6 are high-quality clients, 4 are common clients, and a machine learning algorithm is applied to establish a high-quality client identification model.
The specific implementation steps are that a contrast group and an experimental group are set, the contrast group is not applied with the high-quality customer identification method, the experimental group is applied with the high-quality customer identification method, and the service cost provided by the enterprise to the customer and the return amount of the customer to the enterprise before and after the application of the high-quality customer identification method are respectively counted to obtain the following experimental results:
experimental data comparison table
Figure 203833DEST_PATH_IMAGE012
By comparison, the conclusion is finally drawn: the marketing cost of the experimental group is lower than that of the control group, and the experimental group is higher than that of the control group in the client return amount.
According to the data, the method is applied to high-quality client identification, so that the target client can be effectively and comprehensively evaluated, the target client can be quickly and accurately identified, and the overall economic benefit of an enterprise is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (7)

1. A method for identifying a good quality customer, comprising:
step 1: uniformly formatting data to present highlighted data, and balancing the highlighted data;
step 2: constructing an index system by utilizing four main dimensions of credit degree, economic value, development potential and client stability, and fusing the index system together according to machine learning so as to establish a comprehensive evaluation model of client value;
and step 3: constructing a judgment matrix of the identification index, processing data by using a square root method, and constructing a high-quality identification client model through machine learning;
and 4, step 4: and arranging according to the client value evaluation result in a descending order, and identifying by using the high-quality client model.
2. A method for identifying a good quality customer as claimed in claim 1, wherein the method for deriving a model for the comprehensive evaluation of customer value in step 2 comprises:
step 201: the initial credit score is Z, the normal transaction times and default times of the client in the account opening period determine the credit rating, and the client credit score formula is constructed as follows:
Figure DEST_PATH_IMAGE002
wherein z is an initial credit point, eta is a calculation coefficient, n represents the normal transaction times of the customer, and x represents the default transaction times of the customer;
step 202: constructing a customer purchasing ability formula according to the single purchasing amount M and the purchasing frequency N of the customer:
Figure DEST_PATH_IMAGE004
wherein R is the profit margin of the client i for purchasing the product, S is the premium rate paid by the enterprise for the client i, TCO represents the total cost of ownership of the client i, and X and Y are the product purchase conversion frequency and the urgent order modification frequency of the client i respectively;
step 203: establishing a calculation expression of the total term of cooperation with the client according to the intention of cooperation between the client and the enterprise:
Figure DEST_PATH_IMAGE006
wherein the parameter PcRepresenting the disturbance probability of the client, i is the client;
step 204, profit brought by the possibility that the client purchases enterprise products in the future period is built, and an evaluation formula of the potential value of the client is constructed as follows:
Figure DEST_PATH_IMAGE008
wherein, PB isijProbability, PF, of choosing a product or service j for a customer i to purchaseijAnd PVijThe profits and the consumption cost brought to the enterprises after the products or the services j are selected for the client i respectively are obtained, and the PF is obtainedij-PVijThe value of (a) is net profit;
step 205: and integrating the client evaluation indexes, and fusing the credit, economic value, development potential and client stability to construct a comprehensive evaluation model of the client value:
Figure DEST_PATH_IMAGE010
where score is the client credit score, E (i) is the client attitude, VPiFor potential value of the customer, PiCapabilities are purchased for the customer.
3. A method for identifying a good quality client as claimed in claim 2, wherein in step 203, P is used when the client relationship is in the preliminary stagecIs 0.9 and gradually decreases, when the relationship between the client and the enterprise is a cooperative relationship, P is the value ofcIs 0.1.
4. A quality client identification method according to claim 3 wherein said machine-learned metrics of step 3 include client external environmental conditions, client financial conditions, client demand conditions and client growth.
5. A quality client identification method in accordance with claim 4 wherein said client external environmental conditions are weighted by 15.86%; the client financial condition ratio is 22.13%; the customer demand condition ratio is 31.74 percent; the customer growth ratio percentage was 30.3%.
6. A quality client identification method in accordance with claim 5 wherein said step 4 reuses said quality client model for identification in accordance with a client assessment value of the top 5%.
7. A quality client identification method according to claim 6, wherein the data balance processing method in step 1 is to balance the client data by adjusting class weight values, adjusting node probability estimates and adjusting decision thresholds according to different sampling modes.
CN202011499872.9A 2020-12-18 2020-12-18 High-quality customer identification method Withdrawn CN112561339A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011499872.9A CN112561339A (en) 2020-12-18 2020-12-18 High-quality customer identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011499872.9A CN112561339A (en) 2020-12-18 2020-12-18 High-quality customer identification method

Publications (1)

Publication Number Publication Date
CN112561339A true CN112561339A (en) 2021-03-26

Family

ID=75063284

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011499872.9A Withdrawn CN112561339A (en) 2020-12-18 2020-12-18 High-quality customer identification method

Country Status (1)

Country Link
CN (1) CN112561339A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191807A (en) * 2021-04-30 2021-07-30 中国石油天然气股份有限公司 Natural gas customer rating system and method
CN113313572A (en) * 2021-05-28 2021-08-27 上海浦东发展银行股份有限公司 Model identification method based on accumulation fund point-credit customer
CN113591018A (en) * 2021-07-30 2021-11-02 中国联合网络通信集团有限公司 Communication client classification management method, system, electronic device and storage medium
CN115578157A (en) * 2022-11-13 2023-01-06 南京数族信息科技有限公司 Loan-aid platform dynamic routing tool based on supply and demand value matrix combined routing strategy
CN116385195A (en) * 2023-04-19 2023-07-04 福州年科信息科技有限公司 Enterprise intelligent management system based on big data and intelligent office

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191807A (en) * 2021-04-30 2021-07-30 中国石油天然气股份有限公司 Natural gas customer rating system and method
CN113191807B (en) * 2021-04-30 2024-02-09 中国石油天然气股份有限公司 Natural gas customer rating system and method
CN113313572A (en) * 2021-05-28 2021-08-27 上海浦东发展银行股份有限公司 Model identification method based on accumulation fund point-credit customer
CN113591018A (en) * 2021-07-30 2021-11-02 中国联合网络通信集团有限公司 Communication client classification management method, system, electronic device and storage medium
CN115578157A (en) * 2022-11-13 2023-01-06 南京数族信息科技有限公司 Loan-aid platform dynamic routing tool based on supply and demand value matrix combined routing strategy
CN115578157B (en) * 2022-11-13 2023-10-24 南京数族信息科技有限公司 Dynamic routing method of lending assistance platform based on routing strategy
CN116385195A (en) * 2023-04-19 2023-07-04 福州年科信息科技有限公司 Enterprise intelligent management system based on big data and intelligent office
CN116385195B (en) * 2023-04-19 2024-04-12 助流(佛山)科技有限公司 Enterprise intelligent management system based on big data and intelligent office

Similar Documents

Publication Publication Date Title
CN112561339A (en) High-quality customer identification method
CN109063945A (en) A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system
Jamasb et al. Reform and regulation of the electricity sectors in developing countries
CN105160416A (en) Transformer area reasonable line loss prediction method based on principal component analysis and neural network
CN111177389A (en) NLP technology-based classification method, system and storage medium for power charge notification and customer appeal collection
CN110119948B (en) Power consumer credit evaluation method and system based on time-varying weight dynamic combination
CN110097455B (en) Bank customer optimal configuration method and device
CN108596467B (en) Market operation simulation transaction simulation system suitable for electricity selling company
CN109697574A (en) Small customer electricity Risk Identification Method in a kind of electric power
CN108364191A (en) Top-tier customer Optimum Identification Method and device based on random forest and logistic regression
CN112801542A (en) Credit assessment method for electricity utilization client
CN111709791A (en) Power supply marketing service method based on improved feature word weight algorithm
CN112258067A (en) Low-voltage user payment behavior classification method based on Gaussian mixture model clustering algorithm
CN114202403A (en) Credit evaluation method and system based on electric power data
CN114004530A (en) Enterprise power credit score modeling method and system based on sequencing support vector machine
CN113506173A (en) Credit risk assessment method and related equipment thereof
CN112598480A (en) Computer implementation method for inter-provincial medium-long term clean energy electric power transaction recommendation rate
CN113191807B (en) Natural gas customer rating system and method
CN111899122B (en) User decentralized clearing method based on energy storage control
CN117034126A (en) Green power user classification and feature extraction method and system based on knowledge graph
CN117236532B (en) Load data-based electricity consumption peak load prediction method and system
Ge et al. Bank Loan Strategy Based on Evaluation and Decision Model
CN112785118A (en) Monthly power consumption prediction analysis method for small-sized electricity selling company agent user
Rad et al. Investigating the growth and development of distribution sector assets and the impact of inflation
Li et al. Design and Implementation of an Adaptive Market Evolution Retail Settlement Model

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210326

WW01 Invention patent application withdrawn after publication