Car Insurance Claim Probability Prediction

This repository contains the code and resources for a machine learning project focused on developing a predictive model to assess the claim probability for car insurance policies. The project aims to revolutionize the way car insurance claims are evaluated, providing accurate assessments and improving decision-making in the insurance industry.

Problem Statement:

The goal of this project is to develop a predictive model that accurately assesses the claim probability for car insurance policies. By analyzing a comprehensive dataset and employing machine learning techniques, we aim to improve the efficiency and accuracy of claim assessments, leading to optimized risk assessment, premium calculations, and claims management.

Dataset:

The dataset used for this project contains 44 columns and 58,592 rows. It includes various features such as policy tenure, age of car and policyholder, population density, make, airbags, displacement, cylinder, gear box, turning radius, length, width, height, gross weight, ncap rating, and more. The dataset was preprocessed to handle missing values, address skewness, and encode categorical variables appropriately.

Repository Structure

data/: Contains the dataset used for the project. notebooks/: Jupyter notebooks with the code for data preprocessing, EDA, and model development.

Getting Started

To get started with this project, follow these steps:

Clone the repository: git clone https://github.com/A-iLaa/Car_Insurance_Claim_Prediction.git Navigate to the project directory: cd Car_Insurance_Claim_Prediction Install the required dependencies: pip install -r requirements.txt Open the Jupyter notebooks in the notebooks/ directory to explore the code and run the project.

Conclusion

This project demonstrates the potential of machine learning in assessing claim probability for car insurance policies. By leveraging the power of data analysis, feature engineering, and model development, the project aims to optimize risk assessment, premium calculations, and claims management in the insurance industry. The results showcase promising accuracy and offer valuable insights for further advancements in the field.

For more details, refer to the Jupyter notebooks in the notebooks/ directory, which provide a step-by-step walkthrough of the project.

Feel free to explore the code, experiment with different models, and contribute to the project's development. Your feedback and suggestions are highly appreciated!

Acknowledgments

We would like to acknowledge the contributions of the open-source community and the availability of the dataset used in this project.