Code Monkey home page Code Monkey logo

data-science-project-healt-insurance's Introduction

  • Created a prediction to prredict customer that interested in product ansurance
  • Build a model to predict whether policyholders (customers) from last year will also be interested in the Vehicle Insurance provided by the company.
  • Find EDA in datasets to get insight valuable data
  • Plan a communication strategy to reach those customers and optimize the business model.
  • Focused to Purchase Rate

Table of Contents

Project Background

A company that engaged in the insurance sector. Currently, we already have health insurance products and will expand to vehicle insurance.

In this company, we have a Data Science team who asked to build a model to predict whether policyholders (customers) from last year will also be interested in the Vehicle Insurance provided by the company. The number of vehicle grows linearly with its incident numbers

image

image

image

image

Source : https://www.bps.go.id/indicator/17/513/1/jumlah-kecelakaan-korban-mati-luka-berat-luka-ringan-dan-kerugian-materi.html https://www.bps.go.id/indicator/17/57/1/jumlah-kendaraan-bermotor.html

Data PreProcessing

image

There are not missing values and duplicate data, and columns for gender, id, region code are drop because to decreased ML Bias

for outlier used IQR method and this is before after outlier

image

Feature encoding using one hot encoding image

Exploratory Data Analysis

image

Vehicle age that more than 2 years is the rarest fact. and most of people are not previously insured image image

For correlation data image

Modeling ML

Random forest outperformed all other ML models by AUC and F-1 score image

and for feature importance vehicle damage and previously insured are the top strongest factors image

Business Insight and Recomendation

Insight : Highest interest in product among age 41-50 years at 4.17%.

Business Recommendation : Main focused in age range 41-50 for product. image

Insight : Highest positive response customers with a Vehicle Age of 1-2 years at 9.10% and Damage Vehicle at 11.92%

Business Recommendation : Gain more customers in Vehicle Age 1-2 years Gain more customers in Vehicle Damage = Yes

Insight : High percentage positive response for Annual Premium in range 20,000-40,000.

Business Recommendation : Focused product rate for Vehicle Insurance in range 20,000 โ€“ 40,000.

image

Insight : Rendahnya ketertarikan pada produk di kalangan usia muda (20-30) Ketertarikan pada kalangan 41-50 pada produk lebih baik

Solution Recommendation : Meningkatkan ketertarikan terhadap asuransi kendaraan bagi kalangan usia muda (20-30 tahun).

Marketing Plan & Strategy : Memanfaatkan social media sebagai sarana dalam mempromosikan produk dan juga mengedukasi orang-orang akan pentingnya mengasuransikan kendaraannya.

image

data-science-project-healt-insurance's People

Contributors

andiainunnajib avatar

Watchers

 avatar

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.