https://github.com/rohitinu6/warranty-claims-fraud-prediction
This project focuses on detecting fraudulent warranty claims using machine learning techniques.
https://github.com/rohitinu6/warranty-claims-fraud-prediction
data-science eda finance financial-analysis fraud machine-learning machine-learning-algorithms python visualization warranty warranty-claims
Last synced: 3 months ago
JSON representation
This project focuses on detecting fraudulent warranty claims using machine learning techniques.
- Host: GitHub
- URL: https://github.com/rohitinu6/warranty-claims-fraud-prediction
- Owner: rohitinu6
- Created: 2024-12-24T02:27:34.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-02-06T03:21:53.000Z (4 months ago)
- Last Synced: 2025-02-06T04:24:42.764Z (4 months ago)
- Topics: data-science, eda, finance, financial-analysis, fraud, machine-learning, machine-learning-algorithms, python, visualization, warranty, warranty-claims
- Language: Jupyter Notebook
- Homepage:
- Size: 1.45 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Warranty Claims Fraud Prediction
## 📌 Project Overview
This project focuses on detecting fraudulent warranty claims using machine learning techniques. The goal is to identify and prevent fraudulent claims to reduce financial losses.
## 🚀 Features
- Data preprocessing and exploratory data analysis (EDA)
- Fraud detection using machine learning models
- Feature engineering and selection
- Model evaluation and optimization
## 🛠 Tech Stack
- Python
- Pandas, NumPy
- Scikit-learn
- Matplotlib, Seaborn
- Jupyter Notebook
## 📂 Dataset
The dataset includes:
- **Customer Information**
- **Warranty Claim Details**
- **Claim Amount**
- **Product Details**
- **Fraudulent or Legitimate Label**
## 📊 Machine Learning Models Used
- Logistic Regression
- Random Forest Classifier
- Gradient Boosting
- Neural Networks
## 🔥 Results
The models are evaluated based on accuracy, precision, recall, and F1-score. The best model helps in flagging fraudulent claims effectively.
## 📁 Repository Structure
```
📂 Warranty-Claims-Fraud-Prediction
│-- 📁 data (Dataset & processed data)
│-- 📁 notebooks (Jupyter Notebooks)
│-- 📁 models (Trained models)
│-- 📁 images (Code and Results Screenshots)
│-- 📄 README.md (Project documentation)
```
## 🖼 Code and Results
Include images of code and results in the `images` folder. Example:
## 📜 How to Run the Project
1. Clone the repository:
```bash
git clone https://github.com/rohitinu6/Warranty-Claims-Fraud-Prediction.git
```
2. Navigate to the project folder:
```bash
cd Warranty-Claims-Fraud-Prediction
```
3. Install dependencies:
```bash
pip install -r requirements.txt
```
4. Run the Jupyter Notebook or Python scripts to train and test models.
## 🔗 Links
- **GitHub Repository:** [Warranty Claims Fraud Prediction](https://github.com/rohitinu6/Warranty-Claims-Fraud-Prediction.git)
- **Portfolio:** [Rohit Dubey](https://tinyurl.com/dubeyrohit)
- **GitHub Profile:** [rohitinu6](https://github.com/rohitinu6)
- **LinkedIn:** [Rohit Dubey](https://www.linkedin.com/in/rohit-dubey-d/)
- **Twitter/X:** [@rohitdubey003](https://x.com/rohitdubey003)
## 🔖 Tags
`Machine Learning` `Fraud Detection` `Warranty Claims` `Data Science` `Python` `EDA`
## 📝 License
This project is licensed under the [MIT License](https://opensource.org/licenses/MIT).
---
💡 **For any queries or collaboration opportunities, feel free to connect!** 🚀