CN116883068A - Customer loss early warning method and system - Google Patents
Customer loss early warning method and system Download PDFInfo
- Publication number
- CN116883068A CN116883068A CN202310642401.6A CN202310642401A CN116883068A CN 116883068 A CN116883068 A CN 116883068A CN 202310642401 A CN202310642401 A CN 202310642401A CN 116883068 A CN116883068 A CN 116883068A
- Authority
- CN
- China
- Prior art keywords
- merchant
- early warning
- group
- customer
- merchant group
- 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 31
- 238000012423 maintenance Methods 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000012812 general test Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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 provides a customer loss early warning method and a system, which solve the problems that the early warning object of the conventional early warning method is a single user, the early warning analysis needs to be preset with a threshold value and the like, and the early warning precision and the early warning efficiency are limited, and mainly comprise the steps of S1, grouping merchants according to the characteristic information of each merchant; s2, grabbing at least two sets of operation data ring ratios with different periods and spans from each merchant group for analysis, and when the ring ratio data are all in a descending trend, putting the corresponding user group into an early warning pool to be lost; s3, grouping and sorting the guest-dimension managers corresponding to different merchant groups, wherein the sorting rule is the business data size of the merchant group in the last period; and S4, periodically and quantitatively maintaining the merchants in the sorted merchant group and recording maintenance logs.
Description
Technical Field
The application relates to the technical field of customer loss early warning, in particular to a customer loss early warning method and system.
Background
Currently, in the existing customer loss early warning method, related analysts manually analyze related situations of a current customer, determine a loss type (for example, a loss intention type or a loss possibility type) of the current customer, and generate early warning information to early warn related staff.
In the early warning process, an analyst needs to spend a long time to sort the customer data for corresponding analysis, and early warning information is generated manually for early warning, so that the early warning speed is low. Moreover, since the type of loss of the client is determined during early warning often based on manual experience, the determined client needing early warning is likely to have no loss willingness, or the determined client not needing early warning is likely to have stronger loss willingness instead, so that the early warning accuracy is lower.
The prediction object of the conventional early warning algorithm class model is limited only for a single user dimension or the same account number dimension, and the general test model is to check a certain index or several indexes to compare with a specified preset fixed threshold value so as to obtain a prediction result. Obviously, the accuracy of the prediction process is easy to be limited, thereby indirectly causing low early warning efficiency of customer loss and being unfavorable for subsequent saving and maintenance of customers.
Disclosure of Invention
The application aims to overcome the defects of the prior art, and provides a customer loss early warning method and a system capable of carrying out quick early warning and maintenance on customers to be lost.
In order to solve the technical problems, the application adopts the following technical scheme: a customer churn early warning method comprises the following steps:
s1, grouping merchants according to characteristic information of each merchant;
s2, grabbing at least two sets of operation data ring ratios with different periods and spans from each merchant group for analysis, and when the ring ratio data are all in a descending trend, putting the corresponding user group into an early warning pool to be lost;
s3, grouping and sorting the guest-dimension managers corresponding to different merchant groups, wherein the sorting rule is the business data size of the merchant group in the last period;
and S4, periodically and quantitatively maintaining the merchants in the sorted merchant group and recording maintenance logs.
The characteristic information comprises personal grouping willingness of whether the same customer dimension manager service and the actual user are the same person and the merchant.
Further, for any one of the merchant groups, when the ring ratio data is two sets, the step S2 is specifically,
firstly, capturing an actual transaction data set T1 of the first N working periods in a current merchant group, calculating a working day average value P1=T1/N, capturing an actual transaction data set T2 of the first 2N to N working periods in the current merchant group, calculating a working day average value P2=T2/N, and judging a first ring ratio measuring and calculating index K1=P1-P2;
capturing an actual transaction data set T3 of the first n working periods in the current merchant group, calculating a working day average value P3=T3/n, capturing an actual transaction data set T4 of the first 2n to n working periods of the current merchant group, calculating a working day average value P4=T4/n, and judging a second ring ratio measuring and calculating index K2=P3-P4;
if the K1 and the K2 are smaller than 0 at the same time, the current merchant group is placed into the early warning pool to be lost.
Further, the step S4 is specifically,
judging whether the current merchant group has early-warned in the near term,
if yes, discharging the to-be-lost early warning pool, and carrying out the next merchant group loss early warning judgment again;
if not, screening the merchants in the current merchant group, generating tasks, sending the tasks to the corresponding dimension manager, and maintaining and recording the dimension manager.
A customer churn warning system comprising:
the grouping module is used for extracting the characteristic information of each merchant and dividing the merchant groups by the characteristic information;
the analysis module is used for grabbing two sets of business data ring ratios with different periods and spans in each merchant group for analysis, and placing the merchant groups with the two sets of ring ratio data in a descending trend into the loss early warning pool;
the sequencing module is used for enabling the merchant groups in the loss early warning pool to correspond to different customer dimension managers and sequencing according to the business data quantity of the most recent period of the merchant groups;
and the maintenance module is used for reminding a customer maintenance manager to maintain and record the ordered previous users.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of a customer churn warning method as described above when executing the program.
A computer readable medium comprising a memory and a processor, the memory having stored thereon a computer program executable by the processor, characterized by: the computer program is used for realizing the steps of the customer loss early warning method.
Compared with the prior art, the application has the beneficial effects that:
1. the customer dimension manager is assisted to quickly identify and follow up, so that time is saved, and the working efficiency is improved;
2. the systematic identification is accurate and efficient, and the defects of inaccurate statistical identification, wasted working hours and the like of human intervention are overcome;
3. and feedback information is systematically recorded, so that effective communication information can be conveniently and timely reserved, the follow-up analysis and the identification of loss reasons are facilitated, the continuous improvement of defects is facilitated, and the reserved old users are promoted to be reserved.
Drawings
The disclosure of the present application is described with reference to the accompanying drawings. It is to be understood that the drawings are designed solely for the purposes of illustration and not as a definition of the limits of the application. In the drawings, like reference numerals are used to refer to like parts. Wherein:
FIG. 1 schematically shows an overall process flow diagram according to one embodiment of the present application;
fig. 2 schematically shows a schematic diagram of a loop ratio data grabbing process according to an embodiment of the application.
Detailed Description
It is to be understood that, according to the technical solution of the present application, those skilled in the art may propose various alternative structural modes and implementation modes without changing the true spirit of the present application. Accordingly, the following detailed description and drawings are merely illustrative of the application and are not intended to be exhaustive or to limit the application to the precise form disclosed.
An embodiment according to the application is shown in connection with fig. 1 and 2.
In this embodiment, a customer loss early warning method includes the following steps:
s1, grouping merchants according to characteristic information of each merchant;
s2, grabbing at least two sets of operation data ring ratios with different periods and spans from each merchant group for analysis, and when the ring ratio data are all in a descending trend, putting the corresponding user group into an early warning pool to be lost;
s3, grouping and sorting the guest-dimension managers corresponding to different merchant groups, wherein the sorting rule is the business data size of the merchant group in the last period;
and S4, periodically and quantitatively maintaining the merchants in the sorted merchant group and recording maintenance logs.
The above steps are further described below in conjunction with figure 1,
in step 1, the object of the application predicts the churn is a set formed by a plurality of merchants, namely a merchant group, the individual information of a single merchant is marked with appointed dimension characteristic information, the marked characteristic information comprises whether the individual information is the same customer dimension manager service, whether the individual information is the same actual control user, the personal wish of a user and the like, and then merchants with the same characteristic information of a plurality of dimensions are combined into a whole for measurement and calculation, so that the method is different from a mode of a single user dimension or a unified account number dimension for conventional churn early warning, the predicted object is more comprehensive and has higher efficiency.
For the prediction process and step S2, the prediction model adopted in the application is also different from the common early warning model in the market, the conventional early warning test model is generally used for checking one or several indexes and comparing the indexes with a designated preset fixed threshold value to obtain a prediction result, in the application, the corresponding model has no preset fixed threshold value, and a dual ring ratio model is adopted, as shown in fig. 2, namely, the calculation element data of two different time spans (a and B ) of the whole on the time line are collected and then are subjected to ring ratio, and according to the ring ratio result, the result is used as a detection result index, the preset fixed threshold value is not used, and the comparison with the preset threshold value is also not performed, so that the loss target user can be found earlier than the continuous ring ratio reduction.
As shown in fig. 2, after the merchant groups are divided, when the ring ratio data is two sets for any merchant group, the analysis steps are,
firstly, capturing an actual transaction data set T1 of the first N working periods (A) in a current merchant group, calculating a working day average value P1=T1/N, capturing an actual transaction data set T2 of the first 2N to N working day periods (B) in the current merchant group, calculating a working day average value P2=T2/N, and judging a first ring ratio measuring and calculating index K1=P1-P2;
capturing an actual transaction data set T3 of the first n working periods (a) in the current merchant group, calculating a working day average value P3=T3/n, capturing an actual transaction data set T4 of the first 2n to n working periods (b) in the current merchant group, calculating a working day average value P4=T4/n, and judging a second ring ratio measuring and calculating index K2=P3-P4;
if the K1 and the K2 are smaller than 0 at the same time, the current merchant group is placed into the early warning pool to be lost.
After all the merchant groups are analyzed and determined, further screening is still required for the merchant groups in the pre-warning pool to be run off, that is,
firstly, eliminating merchant groups which are early-warned in the near M days in an accurate early-warning list in an early-warning pool to be lost;
and sorting transaction data of the merchant group in the quasi-early-warning list for nearly m days from high to low and corresponding guest dimension managers in groups, screening the first x names of the quasi-early-warning list in each guest dimension manager as a formal merchant churn list, and automatically pushing the system to a customer service manager for accurate professional service of the service manager.
Also, a customer churn warning system comprising:
the grouping module is used for extracting the characteristic information of each merchant and dividing the merchant groups by the characteristic information;
the analysis module is used for grabbing two sets of business data ring ratios with different periods and spans in each merchant group for analysis, and placing the merchant groups with the two sets of ring ratio data in a descending trend into the loss early warning pool;
the sequencing module is used for enabling the merchant groups in the loss early warning pool to correspond to different customer dimension managers and sequencing according to the business data quantity of the most recent period of the merchant groups;
and the maintenance module is used for reminding a customer maintenance manager to maintain and record the ordered previous users.
The early warning system ranks and screens results according to the sequence of indexes, which is not in the common loss early warning. In order to improve the service quality and reduce the churn rate, each customer dimension manager is automatically allocated with limited (configurable number) top quasi-churn merchants aiming at the result system, and the merchants which have been pre-warned in the last days (configurable days) are not pre-warned repeatedly. The accuracy and maintenance efficiency of the early warning process are greatly improved.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application. The technical scope of the present application is not limited to the above description, and those skilled in the art may make various changes and modifications to the above-described embodiments without departing from the technical spirit of the present application, and these changes and modifications should be included in the scope of the present application.
Claims (7)
1. The customer loss early warning method is characterized by comprising the following steps of:
s1, grouping merchants according to characteristic information of each merchant;
s2, grabbing at least two sets of operation data ring ratios with different periods and spans from each merchant group for analysis, and when the ring ratio data are all in a descending trend, putting the corresponding user group into an early warning pool to be lost;
s3, grouping and sorting the guest-dimension managers corresponding to different merchant groups, wherein the sorting rule is the business data size of the merchant group in the last period;
and S4, periodically and quantitatively maintaining the merchants in the sorted merchant group and recording maintenance logs.
2. The customer churn warning method according to claim 1, wherein: the characteristic information comprises personal grouping willingness of whether the same customer dimension manager service and the actual user are the same person and the merchant.
3. The customer churn warning method according to claim 1, wherein: for any one of the merchant groups, when the ring ratio data is two sets, the step S2 is specifically that,
firstly, capturing an actual transaction data set T1 of the first N working periods in a current merchant group, calculating a working day average value P1=T1/N, capturing an actual transaction data set T2 of the first 2N to N working periods in the current merchant group, calculating a working day average value P2=T2/N, and judging a first ring ratio measuring and calculating index K1=P1-P2;
capturing an actual transaction data set T3 of the first n working periods in the current merchant group, calculating a working day average value P3=T3/n, capturing an actual transaction data set T4 of the first 2n to n working periods of the current merchant group, calculating a working day average value P4=T4/n, and judging a second ring ratio measuring and calculating index K2=P3-P4;
if the K1 and the K2 are smaller than 0 at the same time, the current merchant group is placed into the early warning pool to be lost.
4. The customer churn warning method according to claim 1, wherein: the step S4 is specifically described as,
judging whether the current merchant group has early-warned in the near term,
if yes, discharging the to-be-lost early warning pool, and carrying out the next merchant group loss early warning judgment again;
if not, screening the merchants in the current merchant group, generating tasks, sending the tasks to the corresponding dimension manager, and maintaining and recording the dimension manager.
5. A customer churn warning system, comprising:
the grouping module is used for extracting the characteristic information of each merchant and dividing the merchant groups by the characteristic information;
the analysis module is used for grabbing two sets of business data ring ratios with different periods and spans in each merchant group for analysis, and placing the merchant groups with the two sets of ring ratio data in a descending trend into the loss early warning pool;
the sequencing module is used for enabling the merchant groups in the loss early warning pool to correspond to different customer dimension managers and sequencing according to the business data quantity of the most recent period of the merchant groups;
and the maintenance module is used for reminding a customer maintenance manager to maintain and record the ordered previous users.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of a customer churn warning method according to any one of claims 1 to 4 when the program is executed by the processor.
7. A computer readable medium comprising a memory and a processor, the memory having stored thereon a computer program executable by the processor, characterized by: the computer program is configured to implement the steps of a customer churn warning method according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310642401.6A CN116883068A (en) | 2023-06-01 | 2023-06-01 | Customer loss early warning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310642401.6A CN116883068A (en) | 2023-06-01 | 2023-06-01 | Customer loss early warning method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116883068A true CN116883068A (en) | 2023-10-13 |
Family
ID=88265068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310642401.6A Pending CN116883068A (en) | 2023-06-01 | 2023-06-01 | Customer loss early warning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116883068A (en) |
-
2023
- 2023-06-01 CN CN202310642401.6A patent/CN116883068A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537544B (en) | Real-time monitoring method and monitoring system for transaction system | |
US20220358528A1 (en) | Methods and apparatus for self-adaptive time series forecasting engine | |
WO2021052031A1 (en) | Statistical interquartile range-based commodity inventory risk early warning method and system, and computer readable storage medium | |
US20200242134A1 (en) | Method and apparatus for grouping data records | |
CN109961248B (en) | Method, device, equipment and storage medium for predicting waybill complaints | |
US20180101797A1 (en) | Systems and methods for improving sales process workflow | |
CN109753408A (en) | A kind of process predicting abnormality method based on machine learning | |
CN106408325A (en) | User consumption behavior prediction analysis method based on user payment information and system | |
CN116307928A (en) | Object supervision management system | |
CN116579804A (en) | Holiday commodity sales prediction method, holiday commodity sales prediction device and computer storage medium | |
CN115202847A (en) | Task scheduling method and device | |
CN113190426B (en) | Stability monitoring method for big data scoring system | |
CN116308494A (en) | Supply chain demand prediction method | |
US11334790B1 (en) | System and method for recurrent neural networks for forecasting of consumer goods' sales and inventory | |
CN116883068A (en) | Customer loss early warning method and system | |
CN111435472A (en) | Method, device, equipment and storage medium for predicting quantity of components | |
CN115511536A (en) | Method and device for analyzing life-long value of customer | |
CN114520773A (en) | Service request response method, device, server and storage medium | |
CN111353751B (en) | Method and device for reducing batch card supplementing | |
US20220327562A1 (en) | Methods and systems for applying survival analysis models to produce temporal measures of sales productivity | |
CN111930815A (en) | Method and system for constructing enterprise portrait based on industry attribute and business attribute | |
JP2000123096A (en) | Scheduled forwarding quantity calculating method | |
US20240005084A1 (en) | Dynamic electronic document creation assistance through machine learning | |
RU2700397C1 (en) | Computer-implemented method for automated processing and analysis of data to assess the efficiency of execution of instructions | |
WO2020169807A1 (en) | Improved computer-implemented event forecasting and information provision |
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 |