Churn prediction
Churn prediction is about detecting which customers are likely to leave a service or to cancel a subscription to a service. It is a critical prediction for many businesses because acquiring new clients often costs more than retaining existing ones.
Examples: An insurance company wants to reduce churn, or the proportion of customers who switch to a different insurance company. Churn prediction process will be used to identify both the customers who are more likely to churn and the loyal ones.
The problem
In the insurance sector, customer acquisition and retention are equally important, but the former is a much more expensive process. Specifically, the insurance industry has the highest customer acquisition costs of any other industry, with the cost of acquiring new customers being seven to nine times higher than the cost of retaining a customer. Therefore, insurance companies rely on the existing data in their possession, to understand customers’ behaviour and prevent churn either from the company or the policy.
The purpose
Predict customer churn, i.e the percentage of customers ending their relationship with the insurance company in a given period, typically monthly, quarterly or yearly.
The solution
With the use of machine learning and artificial intelligence models which rely on the historical customer data, a more meaningful targeting of customers can be carried out in the process of organising the marketing strategies related to customer retention in the insurance company.
The benefit
The usefulness of the predictive model lies not only in identifying customers likely to renew their insurance policy or not, but in detecting the main factors related to this decision for each individual case. With this information at hand, insurance company executives or insurance consultants can identify the main points that lead to the customer's decision, reformulate or even create more personalised offers, thus improving management of their customer relations. Identifying at-risk customers can lead to more meaningful customer targeting, saving time and money from unnecessary communications. Actuaries can also leverage the model's predictions of the number of customers who will renew and optimize their pricing plans.
Indicative presentation of the data needed
- The first column of the data file must contain the Renewal status of the insurance policy (e.g. 0: Renewal, 1: Cancel) from historical data.
- The following columns of the file should contain the values of historically recorded characteristics such as: Age, Gender, Marital Status, Employment Status, Income, Area of Residence, Sales Channel, Premium, Number of Policies, Number of Complaints, Policy Type, Months since last claim, Education, Customer Lifetime Value, Months since the start of the policy, Number of insurance claims, Amount of insurance claims, Application data, Policy data, etc.
Table 1. Sample table of user input data
|
Churn |
Gender |
Age |
Education |
N. of complaints |
Net customer value |
N. of claims |
|
1 |
F |
19 |
MSc |
0 |
500 |
1 |
|
0 |
M |
32 |
BSc |
0 |
1300 |
0 |
|
0 |
M |
26 |
BSc |
2 |
2000 |
1 |
|
1 |
F |
29 |
High School |
2 |
600 |
0 |
|
|
M |
35 |
BSc |
0 |
1500 |
0 |
System Prerequisites:
- Toolbox accepts xlsx or csv files.
- The first column should contain the data from the target variable (e.g. “Contract Renewal”), the creation of which results from historical customer data.
- The target variable should not contain missing values.
- In case the user wants to make a forecast, he must enter the data of the customers for whom he needs the forecast, in the same file (excel or csv) as the historical data, provided that the first cell which is the target variable will not contain values (see Table 1).
Output:
After the data has been entered by the user and after a short period of time for its automatic analysis:
- a report of the results and the statistical methods used is extracted from the system
- an excel is exported with the forecast results in case the user wants to make a forecast (see Prerequisites 4)
Note: For any clarification you need regarding the content of the use case or any information related to the collection or validity of your data please contact us.
