CN114387017A - Retail customer demand information sample selection method and device based on customer domain - Google Patents
Retail customer demand information sample selection method and device based on customer domain Download PDFInfo
- Publication number
- CN114387017A CN114387017A CN202210002063.5A CN202210002063A CN114387017A CN 114387017 A CN114387017 A CN 114387017A CN 202210002063 A CN202210002063 A CN 202210002063A CN 114387017 A CN114387017 A CN 114387017A
- Authority
- CN
- China
- Prior art keywords
- customer
- retail
- sample
- domain
- retail customer
- 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
- 238000010187 selection method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012795 verification Methods 0.000 claims abstract description 14
- 230000015654 memory Effects 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 5
- 238000011160 research Methods 0.000 claims description 4
- 241000208125 Nicotiana Species 0.000 claims description 2
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims description 2
- 239000002131 composite material Substances 0.000 claims description 2
- 238000007418 data mining Methods 0.000 abstract description 3
- 238000000265 homogenisation Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 235000019504 cigarettes Nutrition 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a retail customer demand information sample selection method and device based on a customer domain, and belongs to the technical field of big data mining and customer classification management. The retail customer domain generation method based on the two-dimensional data characteristics of the customer operation characteristics and the market characteristics performs homogenization division on the retail customers to generate the retail customer domain with common operation characteristics and consumer groups; selecting samples according to the continuity characteristic, the stability characteristic and the honest operation characteristic of operation; compositely calculating a sample comprehensive index by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, and selecting samples according to a proportion by taking the average value of the member sample comprehensive indexes in the domain as a center; and verifying the coverage rate of the sample through historical data, performing recursive verification, and selecting the optimal sample. The sample selection method provided by the invention can give consideration to the homogeneity and the representativeness of the sample, ensures the coverage rate and the comprehensiveness of the screened sample, and provides an accurate data source for subsequent data analysis.
Description
Technical Field
The invention relates to a retail customer demand information sample selection method and device based on a customer domain, and belongs to the technical field of big data mining and customer classification management.
Background
With the rapid development of science and technology, the continuous expansion and popularization of mobile networks, the informatization wave rapidly rolls over the world. Therefore, massive storage data appear in various industries. People realize the importance of information and have higher requirements on information analysis and use, and how to adopt an effective method to mine deep useful information behind data in big data has become the focus and focus of attention of related industries. Currently, a series of data mining related technologies and industries have appeared and developed at a rapid pace.
For enterprises in the retail industry, such as tobacco business enterprises, deep excavation of market demand information is very important, on one hand, the enterprises can effectively organize goods sources according to the market demand information, adjust release strategies, realize accurate release, effectively meet customer demands and improve the economic operation quality of the enterprises; on the other hand, potential requirements of customers are analyzed for basic-level marketing personnel, targeted differentiated services are provided, individual requirements of the customers are effectively met, the profitability of the customers is further enhanced, the improvement of customer relations is facilitated, the stickiness of the customers is enhanced, and the method has important significance for the extension of marketing chains. At present, the deep mining of market demand information is based on the demand information of retail customers, under the condition that the quantity of demand information samples of the retail customers is large, how to effectively select samples is very important, most of the samples are selected based on the probability distribution of the samples at present, the market characteristics and the operation characteristics of the retail customers are not considered, and the coverage rate of the selected samples is not high.
Disclosure of Invention
The invention aims to provide a retail customer demand information sample selection method based on a customer domain, and aims to solve the problems that the market characteristics and the operation characteristics of customers are not considered and the sample coverage rate is low in the conventional sample selection method.
The invention provides a retail customer demand information sample selection method based on a customer domain for solving the technical problem, which comprises the following steps:
1) acquiring a demand information sample of each retail customer in a research area, wherein the sample comprises basic characteristics and operation characteristics of the retail customer, the operation characteristics comprise monthly average sales volume and single value, the basic characteristics comprise market characteristics, and the market characteristics comprise market type, state and business circle;
2) dividing retail customers according to the operating characteristics and market characteristics of the retail customers to generate retail customer domains with common operating characteristics and consumer groups;
3) screening the retail customers in each retail customer domain according to at least one of the operating continuity characteristic, the smoothness characteristic and the integrity operating characteristic to obtain effective retail customer data in each retail customer domain;
4) calculating a sample comprehensive value of each retail customer domain by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, calculating a mean value of the sample comprehensive indexes in each retail customer domain, and selecting effective retail customer data samples in the corresponding retail customer domains according to a set proportion by taking the mean value of the sample comprehensive indexes in each retail customer domain as a center; the brand width refers to the number of the product specifications contained in the historical purchase data of the retail customer n months before.
The invention also provides a retail customer demand information sample selection device based on the customer domain, which comprises: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the customer domain based retail customer demand information collection sample selection method of the present invention via execution of the executable instructions.
The invention divides according to the operation characteristics and the market characteristics to generate the retail client domain with common operation characteristics and consumer groups, thereby ensuring the homogeneity of the operation characteristics and the consumer group characteristics of the retail client domain; meanwhile, the retail customers are screened by utilizing the continuity characteristic, the stability characteristic and the honest operation characteristic, and the comprehensive value of the samples is calculated by taking the monthly average purchase quantity, the monthly average single value and the brand width as the characteristics, so that the representativeness of the selected samples is ensured. Therefore, the sample selection method provided by the invention can give consideration to the homogeneity and the representativeness of the sample, ensures the coverage rate and the comprehensiveness of the screened sample, and provides an accurate data source for subsequent data analysis.
Further, in order to ensure that the generated retail customer domain can fully cover the operation characteristics and the market characteristics, the division process of the step 2) is as follows: segmenting according to two indexes in the operation characteristics to obtain an initial domain; and (4) alternately dividing the initial domain by three indexes of market type, state and business circle to obtain the retail customer domain with common operation characteristics and consumer groups.
Further, in order to realize accurate classification of the operating characteristics, the system is divided into two types of cities and towns and rural areas according to market types, three types of grocery stores, convenience stores for smoking and drinking and other types according to the state of the trade, and three types of residential areas, business government affairs areas and other types according to the business circles.
Further, the continuity characteristic in the step 3) means that the retail customer continuously operates for more than a set time, the check criterion is to trace back the set time from the current time, and the purchase amount per month is not 0; the stability characteristic means that the operation stability index of the retail customer is less than or equal to a set threshold; the integrity management characteristic is that the integrity management level of the retail customer meets the set requirement.
Further, in order to ensure that the screened retail customer data can be effective, the effective retail customer data refers to a specimen which meets the requirements of continuity characteristics, stability characteristics and integrity management characteristics at the same time.
Further, in order to accurately calculate the comprehensive index of the sample, the calculation process of the comprehensive index of the sample in the step 4) is as follows:
normalizing the monthly average purchase quantity, the monthly average single value and the brand width of each retail customer in each customer domain to obtain a corresponding monthly average purchase quantity index, a monthly average single value index and a brand width index;
and carrying out weighted summation on the monthly average purchase quantity index, the monthly average single value index and the brand width index, wherein the result is the sample comprehensive index of the retail customer.
Further, in order to ensure the coverage rate of the selected sample, the method further comprises a step of verifying the sample selected in the step 4), wherein the verification conditions are as follows: the ratio of the customers represented by the selected sample coverage area to the total number of the customers is larger than a set value, and the ratio of the monthly purchase share of the members of the selected sample coverage area to the monthly purchase quantity of all the customers is larger than the set value.
Further, in order to ensure the coverage rate of the selected sample, if the sample selected in step 4) does not satisfy the verification condition, the set proportion in step 4) is adjusted until the verification condition is satisfied.
Drawings
FIG. 1 is a flow chart of a customer domain based retail customer demand information sample selection method of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings.
Method embodiment
The retail customer domain generation method based on the two-dimensional data characteristics of the customer operation characteristics and the market characteristics performs homogenization division on the retail customers to generate the retail customer domain with common operation characteristics and consumer groups; selecting samples according to the continuity characteristic, the stability characteristic and the honest operation characteristic of operation; compositely calculating a sample comprehensive index by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, and selecting samples according to a proportion by taking the average value of the member sample comprehensive indexes in the domain as a center; and verifying the coverage rate of the sample through historical data, performing recursive verification, and selecting the optimal sample. The implementation flow of the method is shown in fig. 1, and the implementation process is embodied.
1. Obtaining and acquiring a demand information sample of each retail customer in a research area.
The invention obtains samples including basic characteristics and business characteristics of retail customers, wherein the business characteristics comprise monthly average sales volume and single value, the basic characteristics comprise market characteristics, and the market characteristics comprise market type, state and business circle. Monthly average sales volume, single value), the selected time span is the complete historical data of the current n months, the single value is calculated by wholesale price (customer purchase price), and the formula is as follows: the single value is n months of purchase amount (yuan)/n months of total purchase amount (bar), the size of n can be set according to actual conditions, for example, n can be 12; the market types are: cities and towns and rural areas, wherein the businesses are grocery stores, convenience stores for smoking and drinking and other three types, and the business circles are residential areas, business government offices and other three types.
2. And carrying out homogenization division on the demand information samples of the retail customers in the research area to generate the retail customer domain with common operation characteristics and consumption groups.
Dividing retail customers into x classes according to the average monthly sales volume by using a K-means algorithm, dividing the retail customers into y classes according to a single value by using the K-means algorithm, and dividing the retail customers into xy initial domains; on the basis, the initial domain is divided into a plurality of retail customer domains by means of cross division according to market types, business types and business circle types, and customers in each customer domain are respectively the same type of monthly average sales volume, the same type of single value, the same market type, the same business circle and the same business state type. As other embodiments, the K-means algorithm herein may also employ other clustering algorithms.
3. And screening the retail customers in each retail customer domain to obtain effective retail customer data in each retail customer domain.
According to the invention, effective samples are selected through the continuity characteristic, the stability characteristic and the honest operation characteristic of operation, wherein the continuity characteristic means that the continuous operation of the zero client of the cigarette exceeds a month (a is less than or equal to n), the check standard is backtracking a month from the current time, and the purchase quantity of each month is not 0; the stability characteristic means that the operation stability index of a client is less than or equal to B, and the honest operation characteristic is (AAA, AA, A, B, C, D) more than B (including B); the effective specimen refers to a specimen which meets the requirements of continuity characteristic, stability characteristic and honest operation characteristic at the same time. The calculation method of the stationarity characteristic index comprises the following steps: the dispersion of the ratio of the historical purchase data of the previous n months of the client to the total monthly purchase amount is amplified by c times, and the stationarity characteristic index is determined to be less than or equal to b to meet the stationarity characteristic requirement through K-value segment clustering. When effective samples are selected, screening can be performed according to any one or two of the operation continuity characteristic, the stability characteristic and the integrity operation characteristic.
4. And selecting effective retail customer data samples in the corresponding retail customer domains by taking the average value of the comprehensive indexes of the samples in each retail customer domain as a center according to a set proportion.
The method calculates the comprehensive sample value in each retail customer domain by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, calculates the mean value of the comprehensive sample indexes in each retail customer domain, and selects the effective retail customer data samples in the corresponding retail customer domains according to a set proportion by taking the mean value of the comprehensive sample indexes in each retail customer domain as the center.
The brand width refers to the number of the product specifications contained in the historical purchase data of the retail customer n months before. When the sample comprehensive value is calculated, the average monthly purchase quantity, the average monthly single value and the brand width are normalized to obtain an average monthly purchase quantity index, an average monthly single value index and a brand width index, the average monthly purchase quantity, the average monthly single value and the brand width are weighted, the average monthly purchase quantity index p 1%, the average monthly single value index p 2% and the brand width index p 3% are weighted (p1+ p2+ p3 is 100), the weighted sum of the three indexes is the sample comprehensive index, the weight of each index can be set according to actual requirements, and if the average monthly purchase quantity index is considered to be important, the weight of each index can be set to be a greater value. The sample comprehensive index of each retail customer can be calculated through the weighted summation, for each retail customer domain, a plurality of screened effective customers exist, in order to select the effective customers in each retail customer domain, the sample comprehensive indexes of all the effective customers in each retail customer domain need to be calculated, the average value needs to be calculated, and the customer which is the latest from the center is selected in proportion by taking the average value of the sample comprehensive indexes in the retail customer domain as the center. The proportion can be set according to experience, the proportion is relatively high for a small number of clients in the retail client domain, the proportion is relatively low for a large number of clients in the retail client domain, for example, the proportion can be selected from 3% to 15%, and the proportion of the selected samples is calculated according to the number of clients which do not perform effective client screening.
In order to ensure the coverage rate of the selected sample, the invention carries out recursive verification on the coverage rate of the sample through historical data, the coverage rate of the sample refers to that the ratio of the clients represented by the domain covered by the sample to the total number of the clients is more than p4 percent and that the ratio of the monthly purchase share of the members of the domain covered by the sample to the monthly purchase quantity of all the clients is more than p4 percent; if the recursive verification means that the sample coverage rate is not met, the sample coverage rate verification is repeated by finely adjusting the sample selection proportion until the sample coverage rate is qualified.
In order to better illustrate the effect of the present invention, the process of the present invention will be described by taking cigarette retail customers as an example. As shown in fig. 1, taking the selection of the retail customer demand information collection sample in a certain market region as an example, 12 months are selected from 2020, 5 months to 2021, 4 months in China, and the basic data and the operation data of 18016 cigarette retail customers in the market include two indexes of the customer operation characteristics, namely monthly average sales volume and single value, the selected time span is complete historical data from the current 12 months, and the single value is calculated by wholesale price (customer purchase price), and the formula is as follows: the single value is 12 months of purchase amount (yuan)/12 months of total purchase amount (bar). The method for dividing the cigarette retail customers into the cigarette retail customer domains with common operating characteristics and consumer groups comprises the following steps: the client is divided into 10 segments by the average monthly sales using the K-means algorithm, 7 segments by a single value using the K-means algorithm, and 70 fields, as detailed in Table 1.
TABLE 1
According to market type 2, business type 3 and business district 3, on the basis of the above 70 domains, the three indexes are crossed, and the customers are divided into 1260 domains, which are detailed in table 2; the number of domains in which a client exists is 618.
TABLE 2
Selecting effective samples according to the continuity characteristic, the stability characteristic and the integrity operation characteristic of operation, wherein the continuity characteristic means that zero customers of the cigarettes continuously operate for more than 8 months, the verification standard is 8 months from the current time, and the purchase amount of each month is not 0; the stability characteristic means that the operation stability index of a client is less than or equal to 0.5, and the honest operation characteristic is (AAA, AA, A, B, C and D) more than B (including B); the effective specimen is a specimen which simultaneously meets the requirements of continuity characteristic, stability characteristic and honest operation characteristic;
the stationarity characteristic means that the operation stationarity index of a client is less than or equal to 0.5, and the calculation method of the stationarity characteristic index comprises the following steps: the dispersion of the ratio of the historical purchase data of the client in the previous 12 months to the total monthly purchase amount is amplified by 10000 times, and the model determines that the stationarity characteristic index is less than or equal to 0.5 to meet the stationarity characteristic requirement through K value 9-segment clustering;
weighting and compounding to calculate a sample comprehensive index by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, and selecting samples according to a proportion by taking the average value of the intra-domain member sample indexes as a center; brand width: the cigarette specification number contained in the historical purchase data of the client in the previous 12 months;
weighted composite calculation sample index: and normalizing the monthly average purchase quantity, the monthly average single value and the brand width to obtain a monthly average purchase quantity index, a monthly average single value index and a brand width index, wherein the monthly average purchase quantity index is 20%, the monthly average single value index is 45%, the brand width index is 35%, and the weighted sum of the three indexes is a sample comprehensive index. Selecting samples according to the proportion: samples are selected according to the number of members in the domain and the 1342 samples are selected according to the method in the domain, wherein the sample selection ratio is shown in the following table 3:
TABLE 3
The sample coverage rate is verified through historical data, and is verified recursively, in this example, the sample coverage rate refers to that the ratio of the number of clients represented by the domain covered by the sample to the total number of clients is greater than 95%, and the ratio of the monthly purchase share of the members of the domain covered by the sample to the monthly purchase amount of all the clients is greater than 95%. And if the sample coverage rate does not meet the requirement, repeating the sample coverage rate verification by finely adjusting the sample selection proportion until the sample coverage rate is qualified. Through recursive verification, 1342 samples are finally selected in the example, clients 17600 are covered, the client coverage rate reaches 96.58%, and the total client sales in the domain covered by the samples accounts for 97.73% of the total sales in the region.
Device embodiment
The retail customer demand information sample selection device based on the customer domain comprises a processor and a memory, wherein the processor executes a computer program stored by the memory to realize the method of the invention for realizing the method embodiment. That is, the method in the above method embodiments should be understood that the flow of the customer domain based retail customer demand information sample selection method may be implemented by computer program instructions. These computer program instructions may be provided to a processor such that execution of the instructions by the processor results in the implementation of the functions specified in the method flow described above.
The processor referred to in this embodiment refers to a processing device such as a microprocessor MCU or a programmable logic device FPGA; the memory referred to in this embodiment includes a physical device for storing information, and generally, information is digitized and then stored in a medium using an electric, magnetic, optical, or the like. For example: various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as hard disk, floppy disk, magnetic tape, magnetic core memory, bubble memory, and U disk; various types of memory, CD or DVD, that store information optically. Of course, there are other ways of memory, such as quantum memory, graphene memory, and so forth.
The apparatus comprising the memory, the processor and the computer program is realized by the processor executing corresponding program instructions in the computer, and the processor can be loaded with various operating systems, such as windows operating system, linux system, android, iOS system, and the like.
As other embodiments, the device can also comprise a display, and the display is used for displaying the selection result for the staff to refer to.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention, as many variations and modifications are possible without departing from the scope of the invention. It is therefore intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that it is the following claims, including all equivalents, that are intended to define the spirit and scope of this invention. The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (9)
1. A retail customer demand information sample selection method based on a customer domain is characterized by comprising the following steps:
1) acquiring a demand information sample of each retail customer in a research area, wherein the sample comprises basic characteristics and operation characteristics of the retail customer, the operation characteristics comprise monthly average sales volume and single value, the basic characteristics comprise market characteristics, and the market characteristics comprise market type, state and business circle;
2) dividing retail customers according to the operating characteristics and market characteristics of the retail customers to generate retail customer domains with common operating characteristics and consumer groups;
3) screening the retail customers in each retail customer domain according to at least one of the operating continuity characteristic, the smoothness characteristic and the integrity operating characteristic to obtain effective retail customer data in each retail customer domain;
4) calculating a sample comprehensive value of each retail customer domain by taking the average monthly purchase quantity, the average monthly single value and the brand width as characteristics, calculating a mean value of the sample comprehensive indexes in each retail customer domain, and selecting effective retail customer data samples in the corresponding customer domains according to a set proportion by taking the mean value of the sample comprehensive indexes in each retail customer domain as a center; the brand width refers to the number of the product specifications contained in the historical purchase data of the retail customer n months before.
2. The customer domain based retail customer demand information sample selection method according to claim 1, wherein the division process of step 2) is as follows: segmenting according to two indexes in the operation characteristics to obtain an initial domain; and (4) alternately dividing the initial domain by three indexes of market type, state and business circle to obtain the retail customer domain with common operation characteristics and consumer groups.
3. The customer domain-based retail customer demand information sample selection method according to claim 2, wherein the method is divided into two categories of cities and towns and rural areas according to market types, three categories of grocery stores, tobacco and wine convenience stores and other categories according to the state of business, and three categories of residential areas, business government areas and other categories according to business circles.
4. The customer domain-based retail customer demand information sample selection method according to claim 1, wherein the continuity characteristic in the step 3) means that the retail customer continuously operates for more than a set time, the verification criterion is a set time traced back from the current time, and the purchase amount per month is not 0; the stability characteristic means that the operation stability index of the retail customer is less than or equal to a set threshold; the integrity management characteristic is that the integrity management level of the retail customer meets the set requirement.
5. The customer domain-based retail customer demand information sample selection method according to claim 1 or 4, wherein the valid retail customer data is a specimen that meets the requirements of continuity feature, smoothness feature and honest operation feature at the same time.
6. The customer domain-based retail customer demand information sample selection method according to claim 1, wherein the sample composite index in the step 4) is calculated as follows:
normalizing the monthly average purchase quantity, the monthly average single value and the brand width of each retail customer in each retail customer domain to obtain a corresponding monthly average purchase quantity index, a monthly average single value index and a brand width index;
and carrying out weighted summation on the monthly average purchase quantity index, the monthly average single value index and the brand width index, wherein the result is the sample comprehensive index of the retail customer.
7. The customer domain based retail customer demand information sample selection method according to claim 1, further comprising the step of verifying the sample selected in step 4) under the conditions of: the ratio of the customers represented by the selected sample coverage area to the total number of the customers is larger than a set value, and the ratio of the monthly purchase share of the members of the selected sample coverage area to the monthly purchase quantity of all the customers is larger than the set value.
8. The customer domain-based retail customer demand information sample selection method according to claim 7, wherein if the sample selected in step 4) does not satisfy the verification condition, the set proportion in step 4) is adjusted until the verification condition is satisfied.
9. A retail customer demand information sample selection apparatus based on a customer domain, the apparatus comprising: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to perform the customer domain based retail customer demand information collection sample selection method of any one of claims 1-8 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210002063.5A CN114387017A (en) | 2022-01-04 | 2022-01-04 | Retail customer demand information sample selection method and device based on customer domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210002063.5A CN114387017A (en) | 2022-01-04 | 2022-01-04 | Retail customer demand information sample selection method and device based on customer domain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114387017A true CN114387017A (en) | 2022-04-22 |
Family
ID=81199804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210002063.5A Pending CN114387017A (en) | 2022-01-04 | 2022-01-04 | Retail customer demand information sample selection method and device based on customer domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387017A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528716A (en) * | 2015-12-03 | 2016-04-27 | 山东烟草研究院有限公司 | Tobacco brand remote intelligent recommendation method facing retailer individual need |
| CN106447397A (en) * | 2016-09-30 | 2017-02-22 | 浪潮软件集团有限公司 | Tobacco retail customer pricing method based on decision tree algorithm |
| CN108038709A (en) * | 2017-11-03 | 2018-05-15 | 平安科技（深圳）有限公司 | Client's sampling pilot marketing method, electronic device and computer-readable recording medium |
| CN109410024A (en) * | 2017-08-17 | 2019-03-01 | 杭州金智塔科技有限公司 | Net borrows Platform Price index analysis method, apparatus, medium and computer system |
| CN110428270A (en) * | 2019-08-07 | 2019-11-08 | 佰聆数据股份有限公司 | The potential preference client recognition methods of the channel of logic-based regression algorithm |
| CN111401942A (en) * | 2020-03-09 | 2020-07-10 | 广东烟草梅州市有限公司 | Intelligent cigarette order recommendation method |
| CN112115129A (en) * | 2020-09-16 | 2020-12-22 | 浪潮软件股份有限公司 | Retail terminal sample sampling method based on machine learning |
| CN112215640A (en) * | 2020-10-09 | 2021-01-12 | 浪潮卓数大数据产业发展有限公司 | Network retail platform shop sampling method based on statistical estimation |
| CN113780861A (en) * | 2021-09-18 | 2021-12-10 | 深圳供电局有限公司 | Component index evaluation method and system based on user daily electric quantity adjustment value |
-
2022
- 2022-01-04 CN CN202210002063.5A patent/CN114387017A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528716A (en) * | 2015-12-03 | 2016-04-27 | 山东烟草研究院有限公司 | Tobacco brand remote intelligent recommendation method facing retailer individual need |
| CN106447397A (en) * | 2016-09-30 | 2017-02-22 | 浪潮软件集团有限公司 | Tobacco retail customer pricing method based on decision tree algorithm |
| CN109410024A (en) * | 2017-08-17 | 2019-03-01 | 杭州金智塔科技有限公司 | Net borrows Platform Price index analysis method, apparatus, medium and computer system |
| CN108038709A (en) * | 2017-11-03 | 2018-05-15 | 平安科技（深圳）有限公司 | Client's sampling pilot marketing method, electronic device and computer-readable recording medium |
| CN110428270A (en) * | 2019-08-07 | 2019-11-08 | 佰聆数据股份有限公司 | The potential preference client recognition methods of the channel of logic-based regression algorithm |
| CN111401942A (en) * | 2020-03-09 | 2020-07-10 | 广东烟草梅州市有限公司 | Intelligent cigarette order recommendation method |
| CN112115129A (en) * | 2020-09-16 | 2020-12-22 | 浪潮软件股份有限公司 | Retail terminal sample sampling method based on machine learning |
| CN112215640A (en) * | 2020-10-09 | 2021-01-12 | 浪潮卓数大数据产业发展有限公司 | Network retail platform shop sampling method based on statistical estimation |
| CN113780861A (en) * | 2021-09-18 | 2021-12-10 | 深圳供电局有限公司 | Component index evaluation method and system based on user daily electric quantity adjustment value |
Non-Patent Citations (1)
| Title |
|---|
| 黄飞杰;郎旭明;尹健康;张卫东;唐靖;: "聚类集成算法在客户细分模型中的应用", 西南科技大学学报, no. 01, 31 March 2020 (2020-03-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472646A (en) | A kind of financial product recommended method and device | |
| CN103370722B (en) | The system and method that actual volatility is predicted by small echo and nonlinear kinetics | |
| Yang et al. | Analysis of linkage effects among industry sectors in China’s stock market before and after the financial crisis | |
| Park et al. | Explainability of machine learning models for bankruptcy prediction | |
| WO2023082969A1 (en) | Data feature combination pricing method and system based on shapley value and electronic device | |
| CN111222976A (en) | Risk prediction method and device based on network diagram data of two parties and electronic equipment | |
| Nam et al. | City size distribution as a function of socioeconomic conditions: an eclectic approach to downscaling global population | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN111080178A (en) | Risk monitoring method and device | |
| CN110458668A (en) | Determine the method and device of Products Show algorithm | |
| Drosos et al. | Retail customers’ satisfaction with banks in Greece: A multicriteria analysis of a dataset | |
| CN112950359B (en) | User identification method and device | |
| Pérez-Molina | Exploring a multilevel approach with spatial effects to model housing price in San José, Costa Rica | |
| Wang et al. | Future development trend of “new retail” and e-commerce based on big data | |
| CN109767333A (en) | Select based method, device, electronic equipment and computer readable storage medium | |
| CN114387017A (en) | Retail customer demand information sample selection method and device based on customer domain | |
| CN114943563A (en) | Rights and interests pushing method and device, computer equipment and storage medium | |
| CN113837843A (en) | Product recommendation method, device, medium and electronic equipment | |
| Şahin et al. | Application of random forest algorithm for the prediction of online food delivery service delay | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| Barcelos et al. | City ranking based on financial flux indicator clustering | |
| Bartolome | How has India's Rapidly Growing ICT Sector Impacted its Rural Poor? | |
| CN111951099A (en) | Credit card issuing model and application method thereof | |
| Hutapea et al. | Comparison of Accuracy Between Two Methods: Naїve Bayes Algorithm and Decision Tree-J48 to Predict The Stock Price of Pt Astra International tbk Using Data From Indonesia Stock Exchange | |
| Suwirya et al. | Evaluation of ATM Location Placement Using the K-Means Clustering in BNI Denpasar Regional Office |
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 |