Client Needs & Objectives
Context:
- Massive clients databases are not fully exploited
- The use of a machine learning modelling enables to offer additional options and products depending on clients’ characteristics
- A good modelling of customers’ specifications allows for efficient targeting and high probability of complementary options underwriting
Objectives:
Exploitation of customers databases in order to refine the insurance offer of products and complementary options according to clients’ profiles
Scope:
- Insurance policies proposals
- Fraud detection
- Credit risk
Techniques:
- Logistic regression
- Neural network
- Random forest
Our approach
- Segmentation of the database in 2 sub-bases: the first sub-base as a learning tool and the second one for model testing
- Initialization of coefficients and calibration of parameters via machine learning modelling in the learning base to optimize the predictive power on the test base
- Extension of the model to the entire base
- Exploitation of the data with different machine learning models
- Selection of the best model through cross-validation
- Focus on the three products or additional options the most likely to be underwritten
