Analytics_Vidhya_Dataverse_Hackathon

This repository contains the notebook which we used for Analytics Vidhya Dataverse Hack Insurance Claim Prediction competition. With this notebook our team could get the 1st rank in the competition.

Problem Statement

CarIns is a startup that provides insurance for cars. It is one of the best car insurance brands known for the highest claim settlement ratio. It was launched back in Oct 2020 and acquired its initial policyholders by providing a hassle-free claim process, instant policy issuance, and claim settlements at minimum coverages.

As it's a fast growing startup, the company would like to optimize the cost of the insurance by identifying the policyholders who are more likely to claim in the next 6 months.

Now the company would like to use Data Science to identify the policyholders whose chances of filing a claim are high in the next 6 months. The company challenges the Data Science community to build a high-performance algorithm to predict if the policyholder will file a claim in the next 6 months or not based on the set of car and policy features.

About the Dataset

You are provided with information on policyholders containing the attributes like policy tenure, age of the car, age of the car owner, population density of the city, make and model of the car, power, engine type, etc and the target variable indicating whether the policyholder files a claim in the next 6 months or not.