CN112465544A - User loss early warning method and device - Google Patents
User loss early warning method and device Download PDFInfo
- Publication number
- CN112465544A CN112465544A CN202011340761.3A CN202011340761A CN112465544A CN 112465544 A CN112465544 A CN 112465544A CN 202011340761 A CN202011340761 A CN 202011340761A CN 112465544 A CN112465544 A CN 112465544A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- early warning
- store
- sample
- 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 30
- 238000012549 training Methods 0.000 claims abstract description 58
- 238000012360 testing method Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 abstract description 9
- 230000006399 behavior Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007619 statistical method 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
Abstract
The invention discloses a method and a device for early warning user loss. Wherein, the method comprises the following steps: acquiring historical user data; generating a data set according to historical user data; performing model training according to a training set and a test set in the data set to obtain a user loss early warning model; and analyzing the user data according to the user loss early warning model to obtain early warning results for user classification. The invention solves the technical problem of lack of an early warning mechanism caused by acquiring user group analysis according to the traditional statistical mode in the prior art.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a method and a device for early warning user loss.
Background
The concept of 'increasing hackers' is proposed in the U.S. Internet venture in the early years, and an accurate, low-cost and efficient marketing mode is sought. The user is rapidly increased by means of the mobile internet dividend, but with the gradual disappearance of the mobile internet traffic dividend and the increase of the customer acquisition cost, more and more enterprises and brands pay more attention to the user increase, and how to drive the user increase through fine operation is considered. As the big data is more and more widely applied and approved, the big data also begins to play an important role in the user refinement operation. For example, the big data is widely applied to the directions of user update, content intelligent recommendation, intelligent marketing, user loss early warning and the like, and low-cost and high-efficiency refined operation can be realized.
In the field of user loss early warning, a user group is analyzed in an isolated manner by means of statistics based on the aspects of user attribute analysis, key event analysis, negative experience user analysis, service viscosity analysis, activity analysis and the like. By this means, the lost user population can often be found, but it is late.
Most of the existing user loss technologies are analyzed based on statistical means. Based on the user attributes, key events, negatively experienced users, service viscosity, liveness and other angles, the basic attributes of the users are known, and the attribute difference of active users and inactive users can be indirectly distinguished. A lost user population can be indirectly determined by a single angle or multiple isolated angles, but later. Once lost, the user is difficult to recall, so that the function of early warning is not achieved. In the specific user refinement operation process, the fact that the lost user cannot be recovered by the method can not be achieved.
The biggest defect of the prior art is that the early warning of the lost user cannot be carried out in advance, so that the user loss is avoided. The analysis means of the prior art is simple and easy, and is not designed for the loss of users, only the result of the loss of users is analyzed, but the reason of the loss of users is not found, and the loss caused by the loss of users cannot be avoided.
Aiming at the problem that the user group analysis is obtained according to the traditional statistical method in the prior art, so that an early warning mechanism is lacked, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for early warning of user loss, which at least solve the technical problem of lack of an early warning mechanism caused by acquiring user group analysis according to a traditional statistical mode in the prior art.
According to an aspect of an embodiment of the present invention, a method for user churn early warning is provided, including: acquiring historical user data; generating a data set according to historical user data; performing model training according to a training set and a test set in the data set to obtain a user loss early warning model; and analyzing the user data according to the user loss early warning model to obtain early warning results for user classification.
Optionally, the obtaining of the historical user data includes: in the case that the historical user data comprises behavior data, arrival store data and user attribute data of the users within the preset time range, according to the behavior data, arrival store data and user attribute data of the users within the preset time range in the historical user data, the arrival store data of each user at intervals of each time are regarded as first samples, the users who arrive at the store for multiple times are divided into second samples, and the users who do not arrive at the store are regarded as third samples.
Further, optionally, generating the data set according to the historical user data comprises: extracting user attributes and behavior attributes of the historical interval period according to the first sample to serve as characteristics of the sample; processing the historical interval duration into a regression value of the first sample; and carrying out data cleaning and processing according to the first sample, the characteristics of the first sample and the regression value to obtain a data set.
Optionally, performing model training according to a training set and a test set in the data set, and obtaining a user loss early warning model includes: dividing a data set into a training set test set; and training through a regression model according to the training set and the testing set to obtain a user loss early warning model.
Optionally, analyzing the user data according to the user loss early warning model, and obtaining the early warning result of user classification includes: under the condition that the user data comprises data of the last time of each user to the store, determining the data of the last time of each user to the store as a prediction sample of the user churn early warning model; calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user; comparing the time length from the optimal interval to the store with the time length from the last time of the user to the store till now to obtain the user classification to which the user belongs; and generating an early warning result according to the user classification.
Further, optionally, the user classification includes: a client stage, an attrition user early warning stage or an attrition user stage is maintained.
According to another aspect of the embodiments of the present invention, there is also provided a device for user churn early warning, including: the acquisition module is used for acquiring historical user data; the data generation module is used for generating a data set according to historical user data; the training module is used for carrying out model training according to a training set and a test set in the data set to obtain a user loss early warning model; and the analysis module is used for analyzing the user data according to the user loss early warning model to obtain early warning results for user classification.
Optionally, the obtaining module includes: and the acquisition unit is used for regarding the data of every interval from the user to the store of each user as a first sample, regarding the users who arrive at the store for multiple times as a second sample, and regarding the users who do not arrive at the store as a third sample according to the behavior data, the arrival data and the user attribute data of the users within the preset time range in the historical user data.
Further, optionally, the data generating module includes: the characteristic generating unit is used for extracting the user attribute and the behavior attribute of the historical interval period as the characteristic of the sample according to the first sample; the numerical value acquisition unit is used for processing the historical interval duration into a regression value of the first sample; and the data set acquisition unit is used for cleaning and processing data according to the first sample, the characteristics of the first sample and the regression value to obtain a data set.
Optionally, the training module includes: the dividing unit is used for dividing the data set into a training set test set; and the training unit is used for training through the regression model according to the training set and the test set to obtain a user loss early warning model.
Optionally, the analysis module includes: the sample acquisition unit is used for determining the data of the last time to store time of each user as a prediction sample of the user loss early warning model under the condition that the user data comprises the data of the last time to store time of each user; the calculation unit is used for calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user; the analysis unit is used for comparing the time length from the last time of the user to the store to the present time according to the optimal interval to the store so as to obtain the user classification to which the user belongs; and the result generating unit is used for generating an early warning result according to the user classification.
In the embodiment of the invention, historical user data is acquired; generating a data set according to historical user data; performing model training according to a training set and a test set in the data set to obtain a user loss early warning model; the user data is analyzed according to the user loss early warning model to obtain early warning results for user classification, and the purpose of effectively determining whether the user can be lost is achieved, so that the technical effect of providing an effective early warning mechanism is achieved, and the technical problem that the early warning mechanism is lacked due to the fact that user group analysis is obtained according to a traditional statistical mode in the prior art is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart illustrating a method for user churn warning according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an implementation flow of a method for user churn warning according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a device for user churn warning according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided a method embodiment of a method for user churn warning, it is noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer executable instructions and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that presented herein.
Fig. 1 is a schematic flowchart of a method for user churn warning according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step S102, obtaining historical user data;
optionally, the obtaining of the historical user data includes: in the case that the historical user data comprises behavior data, arrival store data and user attribute data of the users within the preset time range, according to the behavior data, arrival store data and user attribute data of the users within the preset time range in the historical user data, the arrival store data of each user at intervals of each time are regarded as first samples, the users who arrive at the store for multiple times are divided into second samples, and the users who do not arrive at the store are regarded as third samples.
Step S104, generating a data set according to historical user data;
further, optionally, generating the data set according to the historical user data comprises: extracting user attributes and behavior attributes of the historical interval period according to the first sample to serve as characteristics of the sample; processing the historical interval duration into a regression value of the first sample; and carrying out data cleaning and processing according to the first sample, the characteristics of the first sample and the regression value to obtain a data set.
Step S106, performing model training according to a training set and a test set in a data set to obtain a user loss early warning model;
optionally, performing model training according to a training set and a test set in the data set, and obtaining a user loss early warning model includes: dividing a data set into a training set test set; and training through a regression model according to the training set and the testing set to obtain a user loss early warning model.
And S108, analyzing the user data according to the user loss early warning model to obtain early warning results for user classification.
Optionally, analyzing the user data according to the user loss early warning model, and obtaining the early warning result of user classification includes: under the condition that the user data comprises data of the last time of each user to the store, determining the data of the last time of each user to the store as a prediction sample of the user churn early warning model; calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user; comparing the time length from the optimal interval to the store with the time length from the last time of the user to the store till now to obtain the user classification to which the user belongs; and generating an early warning result according to the user classification.
Further, optionally, the user classification includes: a client stage, an attrition user early warning stage or an attrition user stage is maintained.
Specifically, with reference to steps S102 to S108, as shown in fig. 2, fig. 2 is a schematic flow chart of an execution process in the user churn early warning method according to an embodiment of the present invention, where the user churn early warning method provided in the embodiment of the present invention specifically includes:
step 1: the behavior data, the arrival data and the user attribute data of the e-commerce user are combed, the data of every interval of each user to the store is regarded as one sample, the users arriving at the store for multiple times are divided into multiple samples, and the users not arriving at the store are regarded as a single sample. Data from a historical interval to a store are processed into a training set and a testing set by a model, each user is predicted by the model obtained by training, and then the user is judged to be in any state of a customer holding stage, a loss user early warning stage and a loss user stage.
Step 2: the data from the historical interval to the store is used as a single sample of the model, the user attribute, the behavior attribute and the like in the historical interval period are extracted and processed as the characteristics of the sample, the historical interval duration is processed as the regression value of the sample, and the historical interval duration can also be called as the optimal interval to the store duration in business. And cleaning and processing the data from the historical interval to the store to obtain a data set required by the regression analysis model.
Step 3: and dividing the data set into a training set and a testing set. By means of a machine learning model, Regression models such as XGB Regressor, Linear Regression, Random forest and the like can be adopted for training to obtain a user loss early warning model.
Step 4: and combing the data of the last store arrival time of each user to the present, processing a prediction sample for early warning of loss of each user, and calculating the optimal store arrival time of each user by means of the user loss early warning model obtained by training.
Step 5: according to the result of model calculation, the optimal store arrival time of the user is compared with the current store arrival time of the user, and the user can be judged to be in any one of a customer keeping stage, a loss user early warning stage and a loss user stage.
The criteria for the user churn phase are shown in table 1:
TABLE 1
Remarking:
(ii) a user optimal interval-to-store duration MT (model time), the user optimal interval-to-store duration calculated by the model.
The last time to store time is up to date, LT (last time), and the last time to store time is up to date.
And thirdly, the parameter P is greater than 1, generally takes a value of 1.2, and can be adjusted according to different service scenes.
In the embodiment of the invention, historical user data is acquired; generating a data set according to historical user data; performing model training according to a training set and a test set in the data set to obtain a user loss early warning model; the user data is analyzed according to the user loss early warning model to obtain early warning results for user classification, and the purpose of effectively determining whether the user can be lost is achieved, so that the technical effect of providing an effective early warning mechanism is achieved, and the technical problem that the early warning mechanism is lacked due to the fact that user group analysis is obtained according to a traditional statistical mode in the prior art is solved.
Example 2
According to another aspect of the embodiments of the present invention, there is also provided a device for user churn early warning, and fig. 3 is a schematic diagram of the device for user churn early warning according to the embodiments of the present invention, as shown in fig. 3, including: an obtaining module 32, configured to obtain historical user data; a data generation module 34 for generating a data set according to the historical user data; the training module 36 is configured to perform model training according to a training set and a test set in the data set to obtain a user loss early warning model; and the analysis module 38 is configured to analyze the user data according to the user loss early warning model to obtain an early warning result for user classification.
Optionally, the obtaining module 32 includes: and the acquisition unit is used for regarding the data of every interval from the user to the store of each user as a first sample, regarding the users who arrive at the store for multiple times as a second sample, and regarding the users who do not arrive at the store as a third sample according to the behavior data, the arrival data and the user attribute data of the users within the preset time range in the historical user data.
Further, optionally, the data generating module 34 includes: the characteristic generating unit is used for extracting the user attribute and the behavior attribute of the historical interval period as the characteristic of the sample according to the first sample; the numerical value acquisition unit is used for processing the historical interval duration into a regression value of the first sample; and the data set acquisition unit is used for cleaning and processing data according to the first sample, the characteristics of the first sample and the regression value to obtain a data set.
Optionally, the training module 36 includes: the dividing unit is used for dividing the data set into a training set test set; and the training unit is used for training through the regression model according to the training set and the test set to obtain a user loss early warning model.
Optionally, the analysis module 38 includes: the sample acquisition unit is used for determining the data of the last time to store time of each user as a prediction sample of the user loss early warning model under the condition that the user data comprises the data of the last time to store time of each user; the calculation unit is used for calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user; the analysis unit is used for comparing the time length from the last time of the user to the store to the present time according to the optimal interval to the store so as to obtain the user classification to which the user belongs; and the result generating unit is used for generating an early warning result according to the user classification.
In the embodiment of the invention, historical user data is acquired; generating a data set according to historical user data; performing model training according to a training set and a test set in the data set to obtain a user loss early warning model; the user data is analyzed according to the user loss early warning model to obtain early warning results for user classification, and the purpose of effectively determining whether the user can be lost is achieved, so that the technical effect of providing an effective early warning mechanism is achieved, and the technical problem that the early warning mechanism is lacked due to the fact that user group analysis is obtained according to a traditional statistical mode in the prior art is solved.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (11)
1. A method for early warning user loss is characterized by comprising the following steps:
acquiring historical user data;
generating a data set according to the historical user data;
performing model training according to the training set and the test set in the data set to obtain a user loss early warning model;
and analyzing the user data according to the user loss early warning model to obtain early warning results for user classification.
2. The method of claim 1, wherein the obtaining historical user data comprises:
and in the case that the historical user data comprises behavior data, arrival store data and user attribute data of the users within the preset time range, according to the behavior data, arrival store data and user attribute data of the users within the preset time range in the historical user data, regarding the arrival store data of each user at each interval as a first sample, regarding the users arriving at the store for multiple times as a second sample, and regarding the users not arriving at the store as a third sample.
3. The method of claim 2, wherein the generating a data set from the historical user data comprises:
extracting user attributes and behavior attributes of the historical interval period according to the first sample to serve as characteristics of the sample;
processing a historical interval duration as a regression value of the first sample;
and carrying out data cleaning and processing according to the first sample, the characteristics of the first sample and the regression value to obtain the data set.
4. The method of claim 1, wherein the performing model training according to the training set and the test set in the data set to obtain a user churn early warning model comprises:
dividing the data set into the training set and the test set;
and training through a regression model according to the training set and the test set to obtain the user loss early warning model.
5. The method of claim 1, wherein analyzing the user data according to the user churn early warning model to obtain early warning results for user classification comprises:
determining the data of each user from last time to store to date as a prediction sample of the user churn early warning model under the condition that the user data comprises the data of each user from last time to store to date;
calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user;
comparing the time length from the optimal interval to the store with the time length from the last time of the user to the store till now to obtain the user classification to which the user belongs;
and generating an early warning result according to the user classification.
6. The method of claim 5, wherein the user classification comprises: a client stage, an attrition user early warning stage or an attrition user stage is maintained.
7. The utility model provides a device of user's early warning that runs off which characterized in that includes:
the acquisition module is used for acquiring historical user data;
the data generation module is used for generating a data set according to the historical user data;
the training module is used for carrying out model training according to a training set and a test set in the data set to obtain a user loss early warning model;
and the analysis module is used for analyzing the user data according to the user loss early warning model to obtain early warning results for user classification.
8. The apparatus of claim 7, wherein the obtaining module comprises:
and the acquisition unit is used for regarding the data of every user from the interval to the store as a first sample, regarding the users from the multiple times to the store as a second sample, and regarding the users not arriving at the store as a third sample according to the behavior data, the arrival data and the user attribute data of the users within the preset time range in the historical user data.
9. The apparatus of claim 8, wherein the data generation module comprises:
the characteristic generating unit is used for extracting the user attribute and the behavior attribute of the historical interval period as the characteristic of the sample according to the first sample;
a numerical value obtaining unit, configured to process a history interval duration as a regression value of the first sample;
and the data set acquisition unit is used for cleaning and processing data according to the first sample, the characteristics of the first sample and the regression value to obtain the data set.
10. The apparatus of claim 7, wherein the training module comprises:
the dividing unit is used for dividing the data set into the training set and the test set;
and the training unit is used for training through a regression model according to the training set and the test set to obtain the user loss early warning model.
11. The apparatus of claim 7, wherein the analysis module comprises:
the sample acquisition unit is used for determining the data of each user from last time to store to date as a prediction sample of the user churn early warning model under the condition that the user data comprises the data of each user from last time to store to date;
the calculation unit is used for calculating according to the user loss early warning model and the prediction sample to obtain the optimal interval store-to-store time of each user;
the analysis unit is used for comparing the time length from the optimal interval to the store with the time length from the last time of the user to the store till now to obtain the user classification to which the user belongs;
and the result generation unit is used for generating an early warning result according to the user classification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011340761.3A CN112465544A (en) | 2020-11-25 | 2020-11-25 | User loss early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011340761.3A CN112465544A (en) | 2020-11-25 | 2020-11-25 | User loss early warning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112465544A true CN112465544A (en) | 2021-03-09 |
Family
ID=74808134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011340761.3A Pending CN112465544A (en) | 2020-11-25 | 2020-11-25 | User loss early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465544A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112052A (en) * | 2021-03-12 | 2021-07-13 | 广东来个碗网络科技有限公司 | Early warning method and device for tableware user loss |
| CN113379452A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Mobile banking customer loss early warning method and system |
| CN113962740A (en) * | 2021-10-27 | 2022-01-21 | 彩虹无线（北京）新技术有限公司 | Early warning method and device for passenger loss of automobile 4S store |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005909A (en) * | 2015-06-17 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Method and device for predicting lost users |
| CN107679686A (en) * | 2017-08-28 | 2018-02-09 | 阿里巴巴集团控股有限公司 | A kind of business performs method and device |
| CN108038711A (en) * | 2017-11-09 | 2018-05-15 | 广州虎牙信息科技有限公司 | Customer loss Forecasting Methodology, device and computer equipment |
| CN111861588A (en) * | 2020-08-06 | 2020-10-30 | 网易（杭州）网络有限公司 | Training method of loss prediction model, player loss reason analysis method and player loss reason analysis device |
-
2020
- 2020-11-25 CN CN202011340761.3A patent/CN112465544A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005909A (en) * | 2015-06-17 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Method and device for predicting lost users |
| CN107679686A (en) * | 2017-08-28 | 2018-02-09 | 阿里巴巴集团控股有限公司 | A kind of business performs method and device |
| CN108038711A (en) * | 2017-11-09 | 2018-05-15 | 广州虎牙信息科技有限公司 | Customer loss Forecasting Methodology, device and computer equipment |
| CN111861588A (en) * | 2020-08-06 | 2020-10-30 | 网易（杭州）网络有限公司 | Training method of loss prediction model, player loss reason analysis method and player loss reason analysis device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112052A (en) * | 2021-03-12 | 2021-07-13 | 广东来个碗网络科技有限公司 | Early warning method and device for tableware user loss |
| CN113379452A (en) * | 2021-06-07 | 2021-09-10 | 广发银行股份有限公司 | Mobile banking customer loss early warning method and system |
| CN113962740A (en) * | 2021-10-27 | 2022-01-21 | 彩虹无线（北京）新技术有限公司 | Early warning method and device for passenger loss of automobile 4S store |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465544A (en) | User loss early warning method and device | |
| US8725746B2 (en) | Filtering information using targeted filtering schemes | |
| CN107797894B (en) | APP user behavior analysis method and device | |
| CN107798027B (en) | Information popularity prediction method, information recommendation method and device | |
| CN106657007A (en) | Method for recognizing abnormal batch ticket booking behavior based on DBSCAN model | |
| CN107818334A (en) | A kind of mobile Internet user access pattern characterizes and clustering method | |
| CN108629379A (en) | A kind of individual's reference appraisal procedure and system | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN111311332A (en) | User data processing method and device | |
| CN110782291A (en) | Advertisement delivery user determination method and device, storage medium and electronic device | |
| CN111881365A (en) | Content recommendation method and device | |
| CN114116872A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| EP2621156A1 (en) | Subscriber portfolio management system | |
| CN111737576A (en) | Application function personalized recommendation method and device | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| Hofgesang et al. | Analysing clickstream data: From anomaly detection to visitor profiling | |
| CN109429296A (en) | For terminal and the associated method, apparatus of internet information and storage medium | |
| JP2000194703A (en) | Method and device for estimating observation information missed in database | |
| CN114663139A (en) | Resource bit processing method and device, storage medium and processor | |
| CN113655958A (en) | Application data storage method | |
| CN111580839B (en) | Upgrading method and device for electrical equipment | |
| CN111127059B (en) | User quality analysis method and device | |
| CN113312902A (en) | Intelligent auditing and checking method and device for same text | |
| CN108694171A (en) | The method and device of information push | |
| CN111309706A (en) | Model training method and device, readable storage medium and electronic equipment |
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 |