CN113781128A - High-potential consumer identification method, system, electronic device, and medium - Google Patents
High-potential consumer identification method, system, electronic device, and medium Download PDFInfo
- Publication number
- CN113781128A CN113781128A CN202111201130.8A CN202111201130A CN113781128A CN 113781128 A CN113781128 A CN 113781128A CN 202111201130 A CN202111201130 A CN 202111201130A CN 113781128 A CN113781128 A CN 113781128A
- Authority
- CN
- China
- Prior art keywords
- consumption
- data
- final
- training
- consumption data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 92
- 238000009826 distribution Methods 0.000 claims abstract description 42
- 238000012360 testing method Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 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
- G06F18/21—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
- 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
- G06Q30/0203—Market surveys; Market polls
Abstract
The application discloses a high-potential consumer identification method, a high-potential consumer identification system, an electronic device and a medium, wherein the high-potential consumer identification method comprises the following steps: acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to obtain final consumption data, and constructing a training data set according to the final consumption data; after the training data set is processed to obtain a final training data set, dividing the final training data set into a training set, a verification set and a test set; training, verifying and testing a learning model through the training set, the verification set and the test set to obtain a prediction model; and inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumers according to the prediction result.
Description
Technical Field
The present application relates to the field of marketing intelligence technologies, and in particular, to a high-latency consumer identification method, system, electronic device, and medium.
Background
The existing marketing theory divides consumers into heavy (heavier) purchasers and light (lighter) purchasers according to the purchase frequency, wherein the high-frequency line is heavy and the low-frequency line is light. General promotional strategies focus more on these heavy consumers. However, a number of studies have shown that these classical theories and strategies have not been successful in anticipation many times. The large amount of data indicates that so-called 20% of high-loyalty customers can typically only contribute to around 50% of sales. There is also a tendency for heavy and light consumers to be reciprocal, i.e. the consumption times of a heavy consumer in a certain brand will decrease and the consumption times of a light consumer will increase within a given period of time. However, how to improve the recognition rate of high-potential consumers and increase sales is an urgent problem to be solved.
Disclosure of Invention
The embodiment of the application provides a high-potential consumer identification method, a high-potential consumer identification system, electronic equipment and a medium, and at least solves the problems of low identification efficiency and the like of consumers with good potential to brands.
The invention provides a high-potential consumer identification method, which comprises the following steps:
acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to obtain final consumption data, and constructing a training data set according to the final consumption data;
after the training data set is processed to obtain a final training data set, dividing the final training data set into a training set, a verification set and a test set;
training, verifying and testing a learning model through the training set, the verification set and the test set to obtain a prediction model;
and inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumers according to the prediction result.
In the above high-potential consumer identification method, after acquiring consumption frequency distribution based on consumption data according to a preset time period and processing the consumption frequency distribution based on a threshold value to obtain final consumption data, constructing a training data set according to the final consumption data includes:
presetting a first time period and a second time period according to the actual sales results;
extracting first consumption data and second consumption data of the client in the first time period and the second time period from a client relation management database;
presetting a re-consumption data threshold and a non-re-consumption data threshold;
after first consumption frequency distribution is obtained through the first consumption data, re-consumption data which are larger than or equal to the re-consumption threshold value are cut off from the first consumption frequency distribution, and first final consumption data are obtained; after second consumption frequency distribution is obtained through the second consumption data, the re-consumption data which are larger than or equal to the re-consumption threshold value are cut off from the second consumption frequency distribution, and second final consumption data are obtained;
and performing intersection processing on the first final consumption data and the second final consumption data of the same consumer, and constructing the training data set through an intersection part.
In the above high-potential consumer identification method, after acquiring the consumption frequency distribution based on the consumption data according to a preset time period and processing the consumption frequency distribution based on a threshold value to obtain final consumption data, the step of constructing a training data set according to the final consumption data further includes:
the training data set includes consumer attribute data and a difference in consumption times.
In the above high-potential consumer recognition method, after the training data set is processed to obtain a final training data set, the step of dividing the final training data set into a training set, a verification set, and a test set includes:
and coding the category type information in the consumer attribute data by adopting a single hot coding method, and normalizing the numerical type information in the consumer attribute data to obtain the final training data set.
In the above method for identifying a high-potential consumer, the step of obtaining a prediction model after training, verifying and testing a learning model through the training set, the verification set and the test set includes:
the learning model is any one of a multilayer perceptron and a support vector machine.
In the method for identifying a high-potential consumer, the step of inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumer according to the prediction result includes:
after third consumption data in a preset third time period are extracted from the customer relationship management database, the third consumption data are coded to obtain third final consumption data;
inputting the third final consumption data into the prediction model, and outputting the prediction result through the prediction model;
and sorting the prediction results, and selecting the consumers corresponding to the prediction results larger than a user-defined consumption threshold value as high-potential consumers.
In the method for identifying a high-potential consumer, the step of inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumer according to the prediction result further includes:
and sequencing the prediction results according to the data size of the prediction results.
The present invention also provides a high-potential consumer identification system, which is suitable for the high-potential consumer identification method described above, and the high-potential consumer identification system includes:
the training data set acquisition unit is used for acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to obtain final consumption data, and then constructing a training data set according to the final consumption data;
the model establishing unit is used for processing the training data set to obtain a final training data set, and then dividing the final training data set into a training set, a verification set and a test set; training, verifying and testing a learning model through the training set, the verification set and the test set to obtain a prediction model;
and the data identification result acquisition unit is used for inputting the third final consumption data into the prediction model to acquire a prediction result and identifying the high-potential consumer according to the prediction result.
The present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements any of the high-potential consumer identification methods described above when executing the computer program.
The present invention also provides an electronic device readable storage medium having stored thereon computer program instructions which, when executed by the processor, implement the high-potential consumer identification method of any one of the above.
Compared with the prior art, the high-potential consumer identification method, the high-potential consumer identification system, the electronic equipment and the medium have the advantages that the light consumer data are obtained by intercepting the heavy consumer data in the consumption data in the set period and performing intersection operation on the intercepted consumption data, and the light consumer and the consumption times data of the light consumer are identified; after the learning model is trained through the light consumer data to construct a consumption time change prediction model, the consumption time change data of the light consumer are predicted through the model. Through the technical scheme, the problems that in the process of identifying the consumers by the brand, the identification efficiency of the consumers with good potential to the brand is low, so that heavy consumers are highly concerned by the brand party to ignore light consumer groups with increasing consumption times or can increase in the future, the brand sales volume is influenced and the like are solved, and the prediction and optimization capabilities are improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of a high-potential consumer identification method according to an embodiment of the present application;
FIG. 2 is a consumption frequency profile according to an embodiment of the present application;
FIG. 3 is a schematic diagram of the high-potential consumer identification system of the present invention;
fig. 4 is a frame diagram of an electronic device according to an embodiment of the present application.
Wherein the reference numerals are:
a training data set acquisition unit: 51;
a model establishing unit: 52;
a data recognition result acquisition unit: 53;
80 parts of a bus;
a processor: 81;
a memory: 82;
a communication interface: 83.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that such a development effort might be complex and tedious, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as a limitation of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
According to the invention, after the prediction model is trained by the consumer consumption data, the change data of the consumer consumption times is predicted by using the prediction model, so that consumers with good potential to brands, namely consumers with gradually increased consumption times, are effectively identified.
The present invention will be described with reference to specific examples.
Example one
The present embodiments provide a high-potential consumer identification method. Referring to fig. 1 to 2, fig. 1 is a flow chart of a high-potential consumer identification method according to an embodiment of the present application; fig. 2 is a consumption frequency distribution diagram according to an embodiment of the present application, and as shown in fig. 1 to 2, the high-potential consumer identification method includes the following steps:
step S1, acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to acquire final consumption data, and constructing a training data set according to the final consumption data;
step S2, after the training data set is processed to obtain a final training data set, the final training data set is divided into a training set, a verification set and a test set;
step S3: training, verifying and testing a learning model through a training set, the verification set and a testing set to obtain a prediction model;
step S4: and inputting the third final consumption data into a prediction model to obtain a prediction result, and identifying the high-potential consumers according to the prediction result.
In the embodiment, after acquiring consumption frequency distribution based on consumption data according to a preset time period and processing the consumption frequency distribution based on a threshold value to obtain final consumption data, the step of constructing a training data set according to the final consumption data includes:
presetting a first time period and a second time period according to the actual sales results;
extracting first consumption data and second consumption data of a customer in a first time period and a second time period from a customer relation management database;
presetting a re-consumption data threshold and a non-re-consumption data threshold;
after first consumption frequency distribution is obtained through the first consumption data, re-consumption data which are larger than or equal to a re-consumption threshold value are cut off from the first consumption frequency distribution, and first final consumption data are obtained; after second consumption frequency distribution is obtained through the second consumption data, the re-consumption data which are larger than or equal to the re-consumption threshold value are cut off from the second consumption frequency distribution, and second final consumption data are obtained;
and performing intersection processing on the first final consumption data and the second final consumption data of the same consumer, and constructing a training data set through the intersection part.
In specific implementation, a first time period and a second time period are preset according to sales performance, and individual consumption data of consumers, which are subjected to consumption behaviors in the past two time periods (such as two years, two quarters, two and a half years and a specific period, which are determined by brand parties according to actual past sales performance), are extracted from a customer relationship management database of a first party owned by the brand (or a second party and a third party); finding out the consumption frequency distribution of the consumers in the latest first time period, wherein the consumption frequency distribution of the consumers is a skewed curve with a long tail, as shown in figure 2, wherein the abscissa is the number of purchases and the ordinate is the percentage of all the consumers; presetting a re-consumption data threshold and a non-re-consumption data threshold, intercepting heavy consumer data (which can be set to be 0.2) according to the re-consumption data threshold to obtain first final consumption data, namely gradually accumulating longitudinal coordinate values (percentage of all consumers) of each column in the graph in fig. 2 from right to left until the accumulation result reaches the set threshold, and reserving the consumer data contained in the rest columns; after the consumption frequency distribution of the consumers in the latest second time period is found out, the data of the heavy consumers are cut off according to the heavy consumption data threshold value to obtain second final consumption data; and intersecting the first final consumption data and the second final consumption data to obtain a training data set.
In an embodiment, after acquiring consumption frequency distribution based on consumption data according to a preset time period and processing the consumption frequency distribution based on a threshold value to obtain final consumption data, the step of constructing a training data set according to the final consumption data further includes:
the training data set includes consumer attribute data and a difference in consumption times.
In a specific implementation, the training data set includes field information including consumer attribute data (e.g., age, gender, education, address, income, etc.) and a difference between the number of consumptions over the last two time periods (the number of consumptions over the last year minus the number of consumptions over the last second year).
In an embodiment, after processing the training data set to obtain a final training data set, segmenting the final training data set into a training set, a validation set, and a test set includes:
and coding the category type information in the consumer attribute data by adopting a single hot coding method, and normalizing the numerical type information in the consumer attribute data to obtain a final training data set.
In a specific implementation, the category-type information (category) in the consumer attribute data is encoded by a one-hot encoding method (one-hot), and the numeric-type information (numeric) in the consumer attribute data is normalized.
In an embodiment, the step of obtaining the prediction model after training, verifying and testing the learning model through the training set, the verification set and the test set comprises:
the learning model is any one of a multilayer perceptron and a support vector machine.
In particular implementations, the final training data set is divided into a training set, a validation set, and a test set at a 6:2:2 ratio, where a 6:2:2 is a classical division that can be divided according to a particular strategy, for example. If an n-fold cross-validation strategy is to be used, 80% of the data can be divided into n shares; selecting a learning model (such as a multilayer perceptron) with a prediction function, training the learning model according to a training set, verifying the learning model through a verification set, testing the learning model through a testing set, and obtaining the prediction model.
In an embodiment, the step of inputting the third final consumption data into a prediction model to obtain a prediction result, and the step of identifying the high-potential consumers according to the prediction result comprises the following steps:
after third consumption data in a preset third time period are extracted from the customer relationship management database, the third consumption data are coded to obtain third final consumption data;
inputting the third final consumption data into a prediction model, and outputting a prediction result through the prediction model;
and sorting the prediction results, and selecting the consumers corresponding to the prediction results larger than a user-defined consumption threshold value as high-potential consumers.
In specific implementation, third consumption data of a consumer with a consumption record of one year is found out from a customer relationship management database, and the third consumption data is coded by using a coding method to obtain third final consumption data; inputting the third final consumption data into a prediction model, and outputting a prediction result by the prediction model after the third final consumption data is predicted by the prediction model; after the prediction results are sorted, according to the customer self-defined consumption threshold values, the consumers corresponding to the prediction results larger than the self-defined consumption threshold values are selected from the sorting results through the computer terminal to be high-potential consumers (namely, consumer data with obviously improved consumption times in the next time period after prediction by the prediction model is obtained).
In an embodiment, the step of inputting the third final consumption data into the prediction model to obtain a prediction result, and the step of identifying the high-potential consumer according to the prediction result further includes:
and sorting the prediction results according to the data size of the prediction results.
Example two
Referring to fig. 3, fig. 3 is a schematic structural diagram of a high-potential consumer identification system according to the present invention. As shown in fig. 3, the high-potential consumer recognition system according to the present invention is applied to the high-potential consumer recognition method described above, and includes:
a training data set obtaining unit 51 configured to obtain consumption frequency distribution based on the consumption data according to a preset time period, process the consumption frequency distribution based on a threshold value to obtain final consumption data, and construct a training data set according to the final consumption data;
the model establishing unit 52 is configured to process the training data set to obtain a final training data set, and then divide the final training data set into a training set, a verification set, and a test set; training, verifying and testing the learning model through a training set, a verifying set and a testing set to obtain a prediction model;
the data identification result acquiring unit 53 inputs the third final consumption data into the prediction model to acquire a prediction result, and identifies the high-potential consumer according to the prediction result.
EXAMPLE III
Referring to fig. 4, this embodiment discloses a specific implementation of an electronic device. The electronic device may include a processor 81 and a memory 82 storing computer program instructions.
Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.
The processor 81 implements any of the high-potential consumer identification methods in the above embodiments by reading and executing computer program instructions stored in the memory 82.
In some of these embodiments, the electronic device may also include a communication interface 83 and a bus 80. As shown in fig. 4, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete communication therebetween.
The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: and data communication is carried out among external equipment, image/abnormal data monitoring equipment, a database, external storage, an image/abnormal data monitoring workstation and the like.
The bus 80 includes hardware, software, or both to couple the components of the electronic device to one another. Bus 80 includes, but is not limited to, at least one of the following: data Bus (DataBus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 80 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (FSB), a Hyper Transport (HT) Interconnect, an ISA (ISA) Bus, an InfiniBand (InfiniBand) Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a PCI (Peripheral Component Interconnect) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Video Electronics Bus (audio Electronics Association), abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 80 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.
The electronic device may be connected to a high-potential consumer identification system to implement the method in conjunction with fig. 1-2.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
In conclusion, the method and the device predict the change of the purchasing times of the light consumers, improve the identification efficiency of the consumers with good potential to brands, enable the brand party to pay attention to the heavy consumers and pay attention to the light consumer groups with increasing or increasing later consumption times, and have great significance for improving the brand sales volume.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the protection scope of the appended claims.
Claims (10)
1. A high-potential consumer identification method, comprising:
acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to obtain final consumption data, and constructing a training data set according to the final consumption data;
after the training data set is processed to obtain a final training data set, dividing the final training data set into a training set, a verification set and a test set;
training, verifying and testing a learning model through the training set, the verification set and the test set to obtain a prediction model;
and inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumers according to the prediction result.
2. The high-potential consumer recognition method according to claim 1, wherein the step of constructing a training data set according to the final consumption data after obtaining the consumption frequency distribution based on the consumption data according to a preset time period and processing the consumption frequency distribution based on a threshold value to obtain the final consumption data comprises:
presetting a first time period and a second time period according to the actual sales results;
extracting first consumption data and second consumption data of the client in the first time period and the second time period from a client relation management database;
presetting a re-consumption data threshold and a non-re-consumption data threshold;
after first consumption frequency distribution is obtained through the first consumption data, re-consumption data which are larger than or equal to the re-consumption threshold value are cut off from the first consumption frequency distribution, and first final consumption data are obtained; after second consumption frequency distribution is obtained through the second consumption data, the re-consumption data which are larger than or equal to the re-consumption threshold value are cut off from the second consumption frequency distribution, and second final consumption data are obtained;
and performing intersection processing on the first final consumption data and the second final consumption data of the same consumer, and constructing the training data set through an intersection part.
3. The high-potential consumer recognition method according to claim 1, wherein the step of constructing a training data set according to the final consumption data after obtaining the consumption frequency distribution based on the consumption data according to the preset time period and processing the consumption frequency distribution based on the threshold value to obtain the final consumption data further comprises:
the training data set includes consumer attribute data and a difference in consumption times.
4. The method of claim 3, wherein the step of segmenting the training data set into a training set, a validation set, and a test set after processing the training data set to obtain a final training data set comprises:
and coding the category type information in the consumer attribute data by adopting a single hot coding method, and normalizing the numerical type information in the consumer attribute data to obtain the final training data set.
5. The high-potential consumer recognition method of claim 1, wherein the step of obtaining a predictive model after training, verifying and testing a learning model through the training set, the verification set and the testing set comprises:
the learning model is any one of a multilayer perceptron and a support vector machine.
6. The method of claim 2, wherein the step of inputting the third final consumption data into the predictive model to obtain a prediction result, and the step of identifying the high-potential consumer according to the prediction result comprises:
after third consumption data in a preset third time period are extracted from the customer relationship management database, the third consumption data are coded to obtain third final consumption data;
inputting the third final consumption data into the prediction model, and outputting the prediction result through the prediction model;
and sorting the prediction results, and selecting the consumers corresponding to the prediction results larger than a user-defined consumption threshold value as high-potential consumers.
7. The high-potential consumer identification method according to claim 6,
the step of inputting the third final consumption data into the prediction model to obtain a prediction result, and identifying the high-potential consumer according to the prediction result further comprises the following steps:
and sequencing the prediction results according to the data size of the prediction results.
8. A high-potential consumer identification system adapted to the high-potential consumer identification method according to any one of claims 1 to 7, the high-potential consumer identification system comprising:
the training data set acquisition unit is used for acquiring consumption frequency distribution based on consumption data according to a preset time period, processing the consumption frequency distribution based on a threshold value to obtain final consumption data, and then constructing a training data set according to the final consumption data;
the model establishing unit is used for processing the training data set to obtain a final training data set, and then dividing the final training data set into a training set, a verification set and a test set; training, verifying and testing a learning model through the training set, the verification set and the test set to obtain a prediction model;
and the data identification result acquisition unit is used for inputting the third final consumption data into the prediction model to acquire a prediction result and identifying the high-potential consumer according to the prediction result.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the high-potential consumer recognition method of any one of claims 1 to 7 when executing the computer program.
10. An electronic device readable storage medium having stored thereon computer program instructions which, when executed by the processor, implement a high-potential consumer identification method as defined in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111201130.8A CN113781128A (en) | 2021-10-15 | 2021-10-15 | High-potential consumer identification method, system, electronic device, and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111201130.8A CN113781128A (en) | 2021-10-15 | 2021-10-15 | High-potential consumer identification method, system, electronic device, and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113781128A true CN113781128A (en) | 2021-12-10 |
Family
ID=78873094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111201130.8A Pending CN113781128A (en) | 2021-10-15 | 2021-10-15 | High-potential consumer identification method, system, electronic device, and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113781128A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150310358A1 (en) * | 2014-04-25 | 2015-10-29 | Mohammad Iman Khabazian | Modeling consumer activity |
CN110046943A (en) * | 2019-05-14 | 2019-07-23 | 华中师范大学 | A kind of optimization method and optimization system of consumer online's subdivision |
CN110111158A (en) * | 2019-05-16 | 2019-08-09 | 创络(上海)数据科技有限公司 | The Marketing Design method, apparatus and storage medium of life cycle or Development phase |
CN110210913A (en) * | 2019-06-14 | 2019-09-06 | 重庆邮电大学 | A kind of businessman frequent customer's prediction technique based on big data |
CN111695042A (en) * | 2020-06-10 | 2020-09-22 | 湖南湖大金科科技发展有限公司 | User behavior prediction method and system based on deep walking and ensemble learning |
-
2021
- 2021-10-15 CN CN202111201130.8A patent/CN113781128A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150310358A1 (en) * | 2014-04-25 | 2015-10-29 | Mohammad Iman Khabazian | Modeling consumer activity |
CN110046943A (en) * | 2019-05-14 | 2019-07-23 | 华中师范大学 | A kind of optimization method and optimization system of consumer online's subdivision |
CN110111158A (en) * | 2019-05-16 | 2019-08-09 | 创络(上海)数据科技有限公司 | The Marketing Design method, apparatus and storage medium of life cycle or Development phase |
CN110210913A (en) * | 2019-06-14 | 2019-09-06 | 重庆邮电大学 | A kind of businessman frequent customer's prediction technique based on big data |
CN111695042A (en) * | 2020-06-10 | 2020-09-22 | 湖南湖大金科科技发展有限公司 | User behavior prediction method and system based on deep walking and ensemble learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112889042A (en) | Identification and application of hyper-parameters in machine learning | |
CN110310114B (en) | Object classification method, device, server and storage medium | |
CN112017040B (en) | Credit scoring model training method, scoring system, equipment and medium | |
CN113010778A (en) | Knowledge graph recommendation method and system based on user historical interest | |
CN109684862B (en) | Data de-identification method and device and computer readable storage medium | |
CN112241904A (en) | Commodity sales prediction method, commodity sales prediction device, computer equipment and storage medium | |
CN112434884A (en) | Method and device for establishing supplier classified portrait | |
CN113592605A (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
CN116071077A (en) | Risk assessment and identification method and device for illegal account | |
CN110245684B (en) | Data processing method, electronic device, and medium | |
CN114782201A (en) | Stock recommendation method and device, computer equipment and storage medium | |
CN113609020A (en) | Test case recommendation method and device | |
CN111898378B (en) | Industry classification method and device for government enterprise clients, electronic equipment and storage medium | |
CN112784572A (en) | Marketing scene conversational analysis method and system | |
CN107622409B (en) | Method and device for predicting vehicle purchasing capacity | |
CN113781128A (en) | High-potential consumer identification method, system, electronic device, and medium | |
CN110544166A (en) | Sample generation method, device and storage medium | |
CN116012066A (en) | Advertisement conversion rate prediction method, device and readable storage medium | |
CN115757973A (en) | Sorting method, device and equipment of recommendation system and readable storage medium | |
CN110634018A (en) | Feature depiction method, recognition method and related device for lost user | |
CN116385039A (en) | Marketing strategy generation method and device and terminal equipment | |
CN113722471A (en) | Text abstract generation method, system, electronic equipment and medium | |
KR102299618B1 (en) | Apparatus and method for matching review advertisement | |
US11366833B2 (en) | Augmenting project data with searchable metadata for facilitating project queries | |
CN112817952A (en) | Data quality evaluation method and system |
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 |