CN113723710A - Customer loss prediction method, system, storage medium and electronic equipment - Google Patents
Customer loss prediction method, system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113723710A CN113723710A CN202111068135.8A CN202111068135A CN113723710A CN 113723710 A CN113723710 A CN 113723710A CN 202111068135 A CN202111068135 A CN 202111068135A CN 113723710 A CN113723710 A CN 113723710A
- Authority
- CN
- China
- Prior art keywords
- customer
- target
- predicted
- function value
- behavior 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006870 function Effects 0.000 claims description 219
- 230000006399 behavior Effects 0.000 claims description 105
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 230000003068 static 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/01—Customer relationship services
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Abstract
The embodiment of the invention provides a customer loss prediction method, a customer loss prediction system, a storage medium and electronic equipment, which can be applied to the field of artificial intelligence or the field of finance. The method comprises the following steps: determining a first function value and a second function value of a customer to be predicted; selecting a customer to be predicted as a first target customer, and judging whether a second target customer exists in a customer set to be predicted, wherein a first function value of the second target customer is larger than a first function value of the first target customer, and a second function value of the second target customer is larger than a second function value of the first target customer; if the second target customer exists, judging whether a third target customer exists, wherein the first function value of the third target customer is smaller than the first function value of the first target customer, and the second function value of the first target customer is smaller than the second function value of the first target customer; if the third target customer does not exist, the first target customer is determined to be the first potential attrition customer. The invention can improve the accuracy of customer loss prediction.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, a system, a storage medium, and an electronic device for predicting customer churn.
Background
As market competition becomes more intense, the costs of maintaining older customers are greatly reduced compared to the costs of developing new customers. Therefore, it is of great importance to the enterprise to maintain relationships with older customers to avoid customer churn. At present, the enterprise often analyzes the characteristics of lost customers according to the experience of actual service personnel to obtain a prediction result for customer loss prediction, and the determined potential lost customers are inaccurate easily caused by the lack of sufficient service knowledge and subjective judgment of the service personnel.
Disclosure of Invention
Embodiments of the present invention provide a customer churn prediction method, a customer churn prediction system, a storage medium, and an electronic device, so as to improve accuracy of customer churn prediction. The specific technical scheme is as follows:
the invention provides a customer churn prediction method, which comprises the following steps:
acquiring a to-be-predicted customer set and customer behavior data of each to-be-predicted customer in the to-be-predicted customer set; the customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client;
determining a first objective function according to the feature type of the first behavior data, and determining a second objective function according to the feature type of the second behavior data;
determining a first function value and a second function value of each customer to be predicted; the first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting the second behavior data into the second objective function;
selecting a customer to be predicted from the customer set to be predicted as a first target customer, and judging whether a second target customer exists in the customer set to be predicted, wherein a first function value of the second target customer is larger than a first function value of the first target customer, and a second function value of the second target customer is larger than a second function value of the first target customer;
if the second target customer exists, judging whether a third target customer exists in the set of customers to be predicted, wherein the first function value of the third target customer is smaller than the first function value of the first target customer, and the second function value of the first target customer is smaller than the second function value of the first target customer;
and if the third target customer does not exist, determining that the first target customer is a first potential attrition customer.
Optionally, after selecting one customer to be predicted from the set of customers to be predicted as the first target customer, the method further includes:
determining the maximum value and the minimum value of the first function values of the clients to be predicted in the client set to be predicted to obtain the maximum first function value and the minimum first function value; determining the maximum value and the minimum value of the second function values of the clients to be predicted in the client set to be predicted to obtain the maximum second function value and the minimum second function value;
determining the first target customer as a first potential attrition customer when the first function value of the first target customer is a maximum first function value and the second function value of the first target customer is a minimum second function value, or when the first function value of the first target customer is a minimum first function value and the second function value of the first target customer is a maximum second function value.
Optionally, the method further comprises:
if the second target customer does not exist or the third target customer exists, storing the first target customer into a first target customer set; customers in the first target set of customers do not include the first potentially attrition customer;
selecting a first target customer from the first target customer set as a fourth target customer, and judging whether a fifth target customer exists in the customer set to be predicted, wherein a first function value of the fifth target customer is smaller than a first function value of the fourth target customer, and a second function value of the fifth target customer is smaller than a second function value of the fourth target customer;
if the fifth target customer exists, determining the number of the fifth target customer, and if the number of the fifth target customer is 1, determining the fourth target customer as a second potential attrition customer; the customer churn probability of the second potentially churned customer is less than the customer churn probability of the first potentially churned customer.
Optionally, after the determining that the fourth target customer is a second potential attrition customer, the method further comprises:
and deleting the first target customer and the fourth target customer in the customer set to be predicted, and taking the remaining customers to be predicted as sixth target customers, wherein the customer churn probability of the sixth target customers is smaller than the customer churn probability of the second potential churn customer.
Optionally, after obtaining the set of customers to be predicted and the customer behavior data of each customer to be predicted in the set of customers to be predicted, the method further includes:
judging whether the characteristic types of the clients to be predicted in the client set to be predicted are the same or not;
if not, the characteristic types of the clients to be predicted are subjected to unification processing.
Optionally, after obtaining the set of customers to be predicted and the customer behavior data of each customer to be predicted in the set of customers to be predicted, the method further includes:
judging whether customer behavior data corresponding to the characteristic types of the customers to be predicted in the customer set to be predicted are abnormal or not;
and if the abnormal customer behavior data are abnormal, replacing the abnormal customer behavior data with preset data.
Optionally, after obtaining the set of customers to be predicted and the customer behavior data of each customer to be predicted in the set of customers to be predicted, the method further includes:
and carrying out normalization processing on the customer behavior data to obtain normalized customer behavior data.
The invention also provides a customer churn prediction system, comprising:
the client data acquisition module is used for acquiring a client set to be predicted and client behavior data of each client to be predicted in the client set to be predicted; the customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client;
the target function determining module is used for determining a first target function according to the characteristic type of the first behavior data and determining a second target function according to the characteristic type of the second behavior data;
the function value determining module is used for determining a first function value and a second function value of each customer to be predicted; the first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting the second behavior data into the second objective function;
a first judging module, configured to select a customer to be predicted from the customer set to be predicted as a first target customer, and judge whether a second target customer exists in the customer set to be predicted, where a first function value of the second target customer is greater than a first function value of the first target customer, and a second function value of the second target customer is greater than a second function value of the first target customer;
a second determining module, configured to determine whether a third target customer exists in the set of customers to be predicted when the second target customer exists, where a first function value of the third target customer is smaller than a first function value of the first target customer, and a second function value of the first target customer is smaller than a second function value of the first target customer;
a first customer churn prediction module to determine the first target customer as a first potential churn customer when the third target customer is not present.
The present invention also provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements the customer churn prediction method described above.
The present invention also provides an electronic device comprising:
at least one processor, and at least one memory, bus connected with the processor;
the processor and the memory complete mutual communication through the bus; the processor is configured to call program instructions in the memory to perform the customer churn prediction method described above.
According to the customer churn prediction method, the customer churn prediction system, the storage medium and the electronic device, a first objective function is determined according to the feature type of first behavior data, and a second objective function is determined according to the feature type of second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client; inputting the first behavior data into a first objective function to obtain a first function value; inputting the second behavior data into a second objective function to obtain a second function value; the activity degree of the customer can be reflected through the first function value, the satisfaction degree of the customer can be reflected through the second function value, whether the customer has the possibility of loss can be determined through the first function value and the second function value, therefore, customer loss prediction is achieved, and the accuracy of customer loss prediction can be improved.
Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a customer churn prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a relationship between predicted customer function values according to an embodiment of the present invention;
FIG. 3 is a block diagram of a customer churn prediction system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
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.
The invention provides a customer churn prediction method, as shown in fig. 1, the method includes:
step 101: and acquiring the customer behavior data of the set of customers to be predicted and each customer to be predicted in the set of customers to be predicted. The customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity level of the client and the second behavior data reflects the satisfaction level of the client.
When customer churn prediction is performed, customers to be predicted in the customer set to be predicted can be selected as bank customers. When collecting bank customer behavior data, the first behavior data reflects the activity degree of the customer, and the first behavior data comprises the estimated annual income A of the customer ═ a1,a2,…,anMean annual customer deposit B ═ B1,b2,…,bnThe year of use of the client C ═ C1,c2,…,cnMean annual transaction times for customers D ═ D1,d2,…,dnThe number of products owned by the customer E ═ E1,e2,…,en}. The second behavior data reflects the satisfaction degree of the customer, and comprises customer online service evaluation data G-G1,g2,…,gnK, offline service evaluation data K ═ K1,k2,…,kn}. n represents the number of clients to be predicted, and the nth client to be predicted has an、bn、cn、dn、en、gn、knA total of 7 eigenvalues.
After step 101, the customer churn prediction method further comprises:
judging whether the characteristic types of the clients to be predicted in the client set to be predicted are the same or not; if not, the characteristic types of the clients to be predicted are subjected to unification processing.
If the customer to be predicted lacks one or more of the 7 feature values, the median value of the feature among all customers to be predicted is substituted for the missing feature value.
After step 101, the customer churn prediction method further comprises:
judging whether customer behavior data corresponding to the characteristic types of the customers to be predicted in the customer set to be predicted are abnormal or not; and if the abnormal customer behavior data are abnormal, replacing the abnormal customer behavior data with preset data.
If the characteristic value of the client to be predicted is abnormal, the abnormal value is replaced by a fixed value 1.
After step 101, the customer churn prediction method further comprises:
and carrying out normalization processing on the client behavior data to obtain normalized client behavior data.
Standardizing the behavior data of the bank customers by using a dispersion standardization method, and carrying out standardization on each dimension characteristic x1,…,xi,…,xnWherein n is the number of clients to be predicted, execute
Obtaining normalized customer behavior data y1,…,yi,…,yn∈[0,1]And completing the standardization of the customer behavior data.
Step 102: and determining a first objective function according to the characteristic type of the first behavior data, and determining a second objective function according to the characteristic type of the second behavior data.
Converting the bank customer loss prediction problem into a multi-objective optimization problem:
min(f1(x)，f2(x)),
x＝(ai,bi,ci,di,ei,gi,ki),ai∈A,bi∈B,ci∈C,di∈D,ei∈E,ki∈K,gi∈G,
wherein f is1(x) Representing a first objective function reflecting the activity of the client; f. of2(x) A second objective function is represented, reflecting customer satisfaction.
The first objective function is generated by carrying out weighted integration on five characteristic types of estimated annual income of customers, annual average deposit of customers, annual number of years of use of customers, annual average transaction times of customers and number of products owned by customers, and the first objective function is as follows:
in the formula, aiRepresenting estimated annual income of the ith bank customer, biRepresenting the annual average deposit of the ith bank customer, ci,Indicating the age of the ith bank customer, diRepresenting the average number of transactions per year, e, for the ith bank customeriIndicating the quantity of the owned products of the ith bank customer.
The bank customer satisfaction is obtained by performing weighted integration on the customer online service evaluation data and the customer offline evaluation data, and the second objective function is as follows:
in the formula, giOn-line service evaluation data, k, representing the ith bank customeriAnd (4) off-line service evaluation data of the ith bank customer.
Step 103: and determining a first function value and a second function value of each customer to be predicted. The first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting the second behavior data into the second objective function.
Step 104: and selecting one customer to be predicted from the customer set to be predicted as a first target customer.
If there are 6 clients to be predicted in the set of clients to be predicted, client 1, client 2, client 3, client 4, client 5 and client 6 are respectively. A customer to be predicted is selected as the first target customer, for example, customer 1 is selected as the first target customer, and then step 105 and step 107 are performed. After the prediction of the client 1 is completed, the remaining clients are selected as the first target clients, and then step 105 and step 107 are performed.
Step 105: and judging whether a second target customer exists in the customer set to be predicted, wherein the first function value of the second target customer is larger than the first function value of the first target customer, and the second function value of the second target customer is larger than the second function value of the first target customer.
Each customer to be predicted in the customer set to be predicted corresponds to a first function value f1And a second function value f2. As shown in FIG. 2, customer 1 corresponds to a function value of (f)1 (1)，f2 (1)) The function value corresponding to client 2 is (f)1 (2)，f2 (2)) The function value corresponding to the client 3 is (f)1 (3)，f2 (3)) The function value corresponding to the client 4 is (f)1 (4)，f2 (4)) The function value corresponding to the client 5 is (f)1 (5)，f2 (5)) The function value corresponding to the client 6 is (f)1 (6)，f2 (6))。
As can be seen from fig. 2:
if customer 1 is the first target customer, then the second target customers are customer 4, customer 5, and customer 6.
If customer 2 is the first target customer, then the second target customer is customer 6.
If customer 3 is the first target customer, then there is no second target customer.
If customer 4 is the first target customer, then the second target customer is customer 6.
If customer 5 is the first target customer, then there is no second target customer.
If customer 6 is the first target customer, then there is no second target customer.
Step 106: and if the second target customer exists, judging whether a third target customer exists in the customer set to be predicted, wherein the first function value of the third target customer is smaller than the first function value of the first target customer, and the second function value of the first target customer is smaller than the second function value of the first target customer.
The first target customers, where the second target customers exist, are customer 1, customer 2, and customer 4.
When the first target customer is customer 1, there is no third target customer.
When the first target customer is customer 2, there is no third target customer.
When the first target customer is customer 4, there is a third customer, customer 1.
Step 107: if the third target customer does not exist, the first target customer is determined to be the first potential attrition customer.
If there are no third target customers that are customer 1 and customer 2, then customer 1 and customer 2 are determined to be the first potential attrition customer.
As can be seen from FIG. 2, the present invention utilizes two function values of customer activity and evaluation to screen two potential attrition customers, namely customer 1 and customer 2, and the first function value f of customer 11 (1)Is the lowest of all customers, and the first function value f of customer 21 (2)And a second function value f2 (2)At a low level among all customers.
As an optional implementation, after step 104, the customer churn prediction method further includes:
determining the maximum value and the minimum value of the first function values of the clients to be predicted in the client set to be predicted to obtain the maximum first function value and the minimum first function value; determining the maximum value and the minimum value of the second function values of the clients to be predicted in the client set to be predicted to obtain the maximum second function value and the minimum second function value;
and determining the first target customer as a first potential attrition customer when the first function value of the first target customer is a maximum first function value and the second function value of the first target customer is a minimum second function value, or when the first function value of the first target customer is a minimum first function value and the second function value of the first target customer is a maximum second function value.
As can be taken from fig. 2, the maximum first function value is f1 (3)The minimum first function value is f1 (1)The maximum second function value is f2 (5)The minimum second function value is f2 (3). Since the first function value of customer 3 is the maximum function value and the second function value of customer 3 is the minimum second function value, customer 3 is determined to be the first potential attrition customer. As can be seen from fig. 2, the first function f of the client 31 (3)And a second function value f2 (3)At a low level among all customers.
As an optional implementation, the customer churn prediction method further includes:
if the second target client does not exist, storing the first target client into a first target client set; if the third target client exists, storing the first target client into the first target client set; wherein none of the customers in the first set of target customers is a first potential attrition customer;
selecting a first target customer from the first target customer set as a fourth target customer, and judging whether a fifth target customer exists in the customer set to be predicted, wherein a first function value of the fifth target customer is smaller than a first function value of the fourth target customer, and a second function value of the fifth target customer is smaller than a second function value of the fourth target customer;
if the fifth target customers exist, determining the number of the fifth target customers, and if the number of the fifth target customers is 1, determining the fourth target customers as second potential attrition customers; the customer churn probability of the second potentially churned customer is less than the customer churn probability of the first potentially churned customer.
If there is no second target customer and not the first potential attrition customer having customer 5 and customer 6, and there is a third target customer and not the first potential attrition customer having customer 4, then there are customer 4, customer 5, and customer 6 in the first set of target customers.
When the fourth target customer is customer 4, there is a fifth target customer that is customer 1.
When the fourth target customer is customer 5, there is a fifth target customer that is customer 1.
When the fourth target customer is customer 6, there are fifth target customers that are customer 1, customer 2, and customer 4.
Customer 4 and customer 5 correspond to a fifth target customer having a customer count of 1, thereby identifying customer 4 and customer 5 as a second potential attrition customer. As can be seen from fig. 2, the first function f of the client 41 (4)And a second function value f2 (4)At a central level among all customers; second function value f of client 52 (5)Although the highest of all customers, the second function f1 (5)But at a lower level among all customers. Overall, the customer churn probability of the second potential churn customer is less than the customer churn probability of the first potential churn customer.
As an optional implementation, after determining that the fourth target customer is the second potential attrition customer, the method further comprises:
and deleting the first target customer and the fourth target customer in the customer set to be predicted, and taking the remaining customers to be predicted as sixth target customers, wherein the customer churn probability of the sixth target customers is smaller than the customer churn probability of the second potential churn customers.
The first target customer and the fourth target customer in the customer set to be predicted are deleted, the remaining customers 6, the customer 6 is used as the sixth target customer, and as can be seen from fig. 2, the first function value f of the customer 61 (6)And a second function value f2 (6)At a higher level among all customers, customer 6 has a lower churn probability than customer 1, customer 2, customer 3, customer 4, and customer 5.
According to the method, the loss of the client is predicted, the client to be predicted is divided according to the loss probability from high to low, various schemes can be formulated for client saving according to different loss probability grades (the loss probability is a first potential loss client, a second potential loss client and a sixth target client from high to low in sequence), the blindness of client saving is solved, and the purpose of stabilizing the client is achieved.
The present invention also provides a customer churn prediction system, as shown in fig. 3, the system includes:
a client data obtaining module 301, configured to obtain a set of clients to be predicted and client behavior data of each client to be predicted in the set of clients to be predicted; the customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client;
an objective function determining module 302, configured to determine a first objective function according to the feature type of the first behavior data, and determine a second objective function according to the feature type of the second behavior data;
a function value determining module 303, configured to determine a first function value and a second function value of each customer to be predicted; the first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting second behavior data into a second objective function;
the client selecting module 304 is configured to select one client to be predicted from the set of clients to be predicted as the first target client.
A first determining module 305, configured to determine whether a second target customer exists in the set of customers to be predicted, where a first function value of the second target customer is greater than a first function value of the first target customer, and a second function value of the second target customer is greater than a second function value of the first target customer;
a second determining module 306, configured to determine whether a third target customer exists in the set of customers to be predicted when a second target customer exists, where a first function value of the third target customer is smaller than a first function value of the first target customer, and a second function value of the first target customer is smaller than a second function value of the first target customer;
a first customer churn prediction module 307, configured to determine the first target customer as a first potential churn customer if the third target customer is not present.
The customer churn prediction system further comprises:
the second customer loss prediction module is used for determining the maximum value and the minimum value of the first function values of the customers to be predicted in the customer set to be predicted to obtain the maximum first function value and the minimum first function value; determining the maximum value and the minimum value of the second function values of the clients to be predicted in the client set to be predicted to obtain the maximum second function value and the minimum second function value; and determining the first target customer as a first potential attrition customer when the first function value of the first target customer is a maximum first function value and the second function value of the first target customer is a minimum second function value, or when the first function value of the first target customer is a minimum first function value and the second function value of the first target customer is a maximum second function value.
The third customer churn prediction module is used for storing the first target customer into the first target customer set if the second target customer does not exist or the third target customer exists; customers in the first set of target customers do not include the first potentially attrition customer; selecting a first target customer from the first target customer set as a fourth target customer, and judging whether a fifth target customer exists in the customer set to be predicted, wherein a first function value of the fifth target customer is smaller than a first function value of the fourth target customer, and a second function value of the fifth target customer is smaller than a second function value of the fourth target customer; if the fifth target customers exist, determining the number of the fifth target customers, and if the number of the fifth target customers is 1, determining the fourth target customers as second potential attrition customers; the customer churn probability of the second potentially churned customer is less than the customer churn probability of the first potentially churned customer.
And the fourth customer churn prediction module is used for deleting the first target customer and the fourth target customer in the customer set to be predicted, taking the remaining customers to be predicted as sixth target customers, wherein the customer churn probability of the sixth target customers is smaller than the customer churn probability of the second potential churn customer.
The customer churn prediction system further comprises:
the unification processing module is used for judging whether the characteristic types of the clients to be predicted in the client set to be predicted are the same or not after the client behavior data of the clients to be predicted in the client set to be predicted and the client behavior data of each client to be predicted in the client set to be predicted are obtained; if not, the characteristic types of the clients to be predicted are subjected to unification processing.
The abnormal processing module is used for judging whether the customer behavior data corresponding to the characteristic types of the customers to be predicted in the customer set to be predicted is abnormal or not after the customer behavior data of the customers to be predicted in the customer set to be predicted and the customer behavior data of each customer to be predicted in the customer set to be predicted are obtained; and if the abnormal customer behavior data are abnormal, replacing the abnormal customer behavior data with preset data.
And the normalization processing module is used for performing normalization processing on the customer behavior data after acquiring the customer behavior data of the customer set to be predicted and the customer behavior data of each customer to be predicted in the customer set to be predicted to obtain normalized customer behavior data.
An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the customer churn prediction method.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, an electronic device 40 includes at least one processor 401, and at least one memory 402 and a bus 403 connected to the processor 401; the processor 401 and the memory 402 complete communication with each other through the bus 403; processor 401 is configured to call program instructions in memory 402 to perform the customer churn prediction method described above. The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to execute a program, when executed on a data processing device, for initializing the steps comprised by the customer churn prediction method as described above.
It should be noted that the customer churn prediction method, the customer churn prediction system, the storage medium and the electronic device provided by the invention can be applied to the field of artificial intelligence or the field of finance. The above description is only an example, and does not limit the application fields of the customer churn prediction method, the customer churn prediction system, the storage medium, and the electronic device provided by the present invention.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, 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.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. 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 an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A customer churn prediction method, comprising:
acquiring a to-be-predicted customer set and customer behavior data of each to-be-predicted customer in the to-be-predicted customer set; the customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client;
determining a first objective function according to the feature type of the first behavior data, and determining a second objective function according to the feature type of the second behavior data;
determining a first function value and a second function value of each customer to be predicted; the first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting the second behavior data into the second objective function;
selecting a customer to be predicted from the customer set to be predicted as a first target customer, and judging whether a second target customer exists in the customer set to be predicted, wherein a first function value of the second target customer is larger than a first function value of the first target customer, and a second function value of the second target customer is larger than a second function value of the first target customer;
if the second target customer exists, judging whether a third target customer exists in the set of customers to be predicted, wherein the first function value of the third target customer is smaller than the first function value of the first target customer, and the second function value of the first target customer is smaller than the second function value of the first target customer;
and if the third target customer does not exist, determining that the first target customer is a first potential attrition customer.
2. The customer churn prediction method as recited in claim 1, wherein after selecting a customer to be predicted from the set of customers to be predicted as the first target customer, the method further comprises:
determining the maximum value and the minimum value of the first function values of the clients to be predicted in the client set to be predicted to obtain the maximum first function value and the minimum first function value; determining the maximum value and the minimum value of the second function values of the clients to be predicted in the client set to be predicted to obtain the maximum second function value and the minimum second function value;
determining the first target customer as a first potential attrition customer when the first function value of the first target customer is a maximum first function value and the second function value of the first target customer is a minimum second function value, or when the first function value of the first target customer is a minimum first function value and the second function value of the first target customer is a maximum second function value.
3. The customer churn prediction method as recited in claim 1, further comprising:
if the second target customer does not exist or the third target customer exists, storing the first target customer into a first target customer set; customers in the first target set of customers do not include the first potentially attrition customer;
selecting a first target customer from the first target customer set as a fourth target customer, and judging whether a fifth target customer exists in the customer set to be predicted, wherein a first function value of the fifth target customer is smaller than a first function value of the fourth target customer, and a second function value of the fifth target customer is smaller than a second function value of the fourth target customer;
if the fifth target customer exists, determining the number of the fifth target customer, and if the number of the fifth target customer is 1, determining the fourth target customer as a second potential attrition customer; the customer churn probability of the second potentially churned customer is less than the customer churn probability of the first potentially churned customer.
4. The customer churn prediction method as recited in claim 3, wherein after the determining the fourth target customer is a second potential churn customer, the method further comprises:
and deleting the first target customer and the fourth target customer in the customer set to be predicted, and taking the remaining customers to be predicted as sixth target customers, wherein the customer churn probability of the sixth target customers is smaller than the customer churn probability of the second potential churn customer.
5. The customer churn prediction method as recited in claim 1, wherein after obtaining the set of customers to be predicted and the customer behavior data for each customer to be predicted in the set of customers to be predicted, the method further comprises:
judging whether the characteristic types of the clients to be predicted in the client set to be predicted are the same or not;
if not, the characteristic types of the clients to be predicted are subjected to unification processing.
6. The customer churn prediction method as recited in claim 1, wherein after obtaining the set of customers to be predicted and the customer behavior data for each customer to be predicted in the set of customers to be predicted, the method further comprises:
judging whether customer behavior data corresponding to the characteristic types of the customers to be predicted in the customer set to be predicted are abnormal or not;
and if the abnormal customer behavior data are abnormal, replacing the abnormal customer behavior data with preset data.
7. The customer churn prediction method as recited in claim 1, wherein after obtaining the set of customers to be predicted and the customer behavior data for each customer to be predicted in the set of customers to be predicted, the method further comprises:
and carrying out normalization processing on the customer behavior data to obtain normalized customer behavior data.
8. A customer churn prediction system comprising:
the client data acquisition module is used for acquiring a client set to be predicted and client behavior data of each client to be predicted in the client set to be predicted; the customer behavior data comprises first behavior data and second behavior data; the first behavior data reflects the activity degree of the client, and the second behavior data reflects the satisfaction degree of the client;
the target function determining module is used for determining a first target function according to the characteristic type of the first behavior data and determining a second target function according to the characteristic type of the second behavior data;
the function value determining module is used for determining a first function value and a second function value of each customer to be predicted; the first function value is obtained by inputting the first behavior data into the first objective function; the second function value is obtained by inputting the second behavior data into the second objective function;
a first judging module, configured to select a customer to be predicted from the customer set to be predicted as a first target customer, and judge whether a second target customer exists in the customer set to be predicted, where a first function value of the second target customer is greater than a first function value of the first target customer, and a second function value of the second target customer is greater than a second function value of the first target customer;
a second determining module, configured to determine whether a third target customer exists in the set of customers to be predicted when the second target customer exists, where a first function value of the third target customer is smaller than a first function value of the first target customer, and a second function value of the first target customer is smaller than a second function value of the first target customer;
a first customer churn prediction module to determine the first target customer as a first potential churn customer when the third target customer is not present.
9. A computer-readable storage medium, having a program stored thereon, which when executed by a processor, implements the customer churn prediction method of any one of claims 1-7.
10. An electronic device, comprising:
at least one processor, and at least one memory, bus connected with the processor;
the processor and the memory complete mutual communication through the bus; the processor is configured to call program instructions in the memory to perform the customer churn prediction method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111068135.8A CN113723710B (en) | 2021-09-13 | 2021-09-13 | Customer loss prediction method, system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111068135.8A CN113723710B (en) | 2021-09-13 | 2021-09-13 | Customer loss prediction method, system, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113723710A true CN113723710A (en) | 2021-11-30 |
| CN113723710B CN113723710B (en) | 2024-02-27 |
Family
ID=78683460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111068135.8A Active CN113723710B (en) | 2021-09-13 | 2021-09-13 | Customer loss prediction method, system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723710B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889724A (en) * | 2019-11-22 | 2020-03-17 | 北京明略软件系统有限公司 | Customer churn prediction method, customer churn prediction device, electronic equipment and storage medium |
| CN112232945A (en) * | 2020-10-15 | 2021-01-15 | 中国农业银行股份有限公司 | Method and device for determining personal customer credit |
| CN112288117A (en) * | 2019-07-23 | 2021-01-29 | 贝壳技术有限公司 | Target customer deal probability prediction method and device and electronic equipment |
| CN112819258A (en) * | 2021-03-24 | 2021-05-18 | 中国工商银行股份有限公司 | Bank branch to store customer quantity prediction method and device |
-
2021
- 2021-09-13 CN CN202111068135.8A patent/CN113723710B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288117A (en) * | 2019-07-23 | 2021-01-29 | 贝壳技术有限公司 | Target customer deal probability prediction method and device and electronic equipment |
| CN110889724A (en) * | 2019-11-22 | 2020-03-17 | 北京明略软件系统有限公司 | Customer churn prediction method, customer churn prediction device, electronic equipment and storage medium |
| CN112232945A (en) * | 2020-10-15 | 2021-01-15 | 中国农业银行股份有限公司 | Method and device for determining personal customer credit |
| CN112819258A (en) * | 2021-03-24 | 2021-05-18 | 中国工商银行股份有限公司 | Bank branch to store customer quantity prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113723710B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20070156479A1 (en) | Multivariate statistical forecasting system, method and software | |
| CN109299178B (en) | Model application method and data analysis system | |
| CA2935281C (en) | A multidimensional recursive learning process and system used to discover complex dyadic or multiple counterparty relationships | |
| JP2017509947A (en) | Obtaining the social relationship type of a network subject | |
| JP6251383B2 (en) | Calculating the probability of a defaulting company | |
| CN112966189A (en) | Fund product recommendation system | |
| CN113538154A (en) | Risk object identification method and device, storage medium and electronic equipment | |
| CN113822488A (en) | Risk prediction method and device for financing lease, computer equipment and storage medium | |
| CN110866698A (en) | Device for assessing service score of service provider | |
| CN114584601A (en) | User loss identification and intervention method, system, terminal and medium | |
| US20220019918A1 (en) | Machine learning feature recommendation | |
| CN113723710A (en) | Customer loss prediction method, system, storage medium and electronic equipment | |
| Han et al. | Using source code and process metrics for defect prediction-A case study of three algorithms and dimensionality reduction. | |
| CN113869423A (en) | Marketing response model construction method, equipment and medium | |
| CN113296951A (en) | Resource allocation scheme determination method and equipment | |
| CN112434083A (en) | Event processing method and device based on big data | |
| TWI634508B (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| CN117391313B (en) | Intelligent decision method, system, equipment and medium based on AI | |
| CN114971697A (en) | Data processing method, device, equipment, storage medium and product | |
| CN117422545A (en) | Credit risk identification method, apparatus, device and storage medium | |
| CN113919838A (en) | Abnormal transaction identification system applying big data to intelligent finance | |
| CN113723865A (en) | Network operation level evaluation method and device, electronic equipment and storage medium | |
| CN116881787A (en) | Data sample classification method and device, processor and electronic equipment | |
| CN116662568A (en) | Method and device for analyzing fund flow direction, storage medium and electronic equipment | |
| CN117459576A (en) | Data pushing method and device based on edge calculation and computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |