Welcome to my Machine Learning portfolio. This repository focuses on applying supervised learning algorithms to solve real-world financial problems, with a primary emphasis on Credit Risk Assessment and Predictive Modeling.
The flagship project in this repo is an end-to-end Credit Score Prediction system. It evaluates the creditworthiness of individuals based on historical financial data.
As seen in the model_flow.png, the project follows a rigorous data science pipeline:
- Data Preprocessing: Handling missing values and feature scaling.
- Feature Engineering: Selecting the most impactful financial indicators.
- Training: Utilizing the XGBoost algorithm for high-performance classification.
- Evaluation: Comparing Actual vs. Predicted results to ensure model reliability.
| File | Category | Description |
|---|---|---|
credit_score_model.py |
FinTech | The primary XGBoost implementation for credit risk. |
Logistic_Regression.py |
Classification | Baseline model for binary financial outcomes. |
KNN.py |
Classification | Instance-based learning for pattern recognition. |
latex code for xgboost... |
Documentation | LaTeX source for the technical report on the model. |
machine learning course.pdf |
Education | A comprehensive guide and notes on ML fundamentals. |
- Language: Python 3.x
- Algorithms: XGBoost, KNN, Logistic Regression
- Reporting: LaTeX (for academic-grade documentation)
- Visualization: Matplotlib, Seaborn
To run the credit scoring model locally:
- Clone the Repo:
git clone https://github.com/Vipeen21/machine-learning-projects.git cd machine-learning-projects - Install Requirements:
pip install xgboost scikit-learn pandas matplotlib
- Run the Model:
python credit_score_model.py
This project is licensed under the MIT License - feel free to use the code for your own financial analysis or learning!
Created and maintained by Vipeen Kumar