Code Monkey home page Code Monkey logo

analytics_vidhya_dataverse_hackathon's Introduction

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.

analytics_vidhya_dataverse_hackathon's People

Contributors

chinmayeeb96 avatar

Stargazers

 avatar

Watchers

 avatar  avatar

Forkers

anandanne

analytics_vidhya_dataverse_hackathon's Issues

Reproducibility

Hi,

I was reading through your approach and tried to replicate it. One question I had was all the feature engineering you did sounds good but does that not leverage the power of catboost using categorical indices? Because once all the feature engineering is done, there is not even one feature as category dtype as everything is either dummy encoded or 1/0 or oridnal. And the performance after feature engineering was slightly lower than when the model leveraged categorical indices.

Any thoughts?

Thanks and Congrats!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.