Customer Insurance Prediction using Machine Learning

📌 Project Overview

The Customer Insurance Prediction project uses Machine Learning to predict whether a customer is likely to purchase an insurance policy based on demographic and financial features such as age, income, and previous insurance history.

This project helps insurance companies improve customer targeting, risk assessment, and decision-making.

---

🎯 Objectives

• Predict insurance purchase behavior of customers
• Analyze customer data to identify key influencing factors
• Improve business decision-making using ML models
• Build an end-to-end ML workflow

---

🛠 Tech Stack

• Programming Language: Python
• Libraries: NumPy, Pandas, Matplotlib, Seaborn
• Machine Learning: Scikit-learn
• Model Used: Logistic Regression / Random Forest (can vary)
• Tools: Jupyter Notebook, Git, GitHub

---

📂 Dataset Description

The dataset contains customer-related attributes such as:

• Age
• Gender
• Annual Income
• Policy history
• Insurance purchase status (Target variable)

The target variable indicates whether the customer purchased insurance (Yes/No).

---

🚀 Features

• Data preprocessing and cleaning
• Exploratory Data Analysis (EDA)
• Feature selection
• Model training and testing
• Accuracy and performance evaluation
• Prediction on new customer data

---

▶️ Project Workflow

1. Load and explore dataset
2. Clean and preprocess data
3. Perform Exploratory Data Analysis
4. Split data into training and testing sets
5. Train ML model
6. Evaluate model performance
7. Make predictions

---

▶️ How to Run the Project

  Clone the repository:

git clone https://github.com/18deepthi/Customer-insurance-prediction.git
Install required libraries:pip install numpy pandas matplotlib seaborn scikit-learn
Run the Jupyter Notebook: jupyter notebook