Insurance company scoring
About project
The expected tariffs for clients and the forecast of unprofitable cases at the beginning of work are calculated. The company became more productive in the insurance market: sales increased by 10%.
Models need to be built to predict customer losses, the size of the loss, and the likelihood of buying and renewing a policy.
A task
Bisiness effect
Building models to predict each case
Solution
Stages of development
Тechnology
3.
Productivity increase
2.
Development of a pilot model
4.
Model Implementation
1.
Data analysis
5.
Model monitoring
An auto ML library to build and implement models in a fast way
Insolver.io
Lightgbm, CatBoost, XGBoost
Libraries for building, boosting models
The generalized linear model (GLiM or GLM) is an advanced statistical modeling technique. Used in all applications of applied statistics.
A set of libraries for building GLM H2O models
Project team
Frank Sh.
Team lead
Alexander S.
Аnalyst
Alexander Kh.
Engineer
Areas of use
This technology is needed by insurance companies. In order to calculate the losses, the amount of losses, the probability of buying a policy, the probability of extending the contract.
These models will help to calculate tariffs for the client and be more competitive in the insurance market.
These models will help to calculate tariffs for the client and be more competitive in the insurance market.
