From predictive modeling to explainable AI, I help businesses make smarter, data-driven decisions.
I am a Data Scientist and Machine Learning Engineer focused on building end-to-end ML systems — from data preprocessing to deployment and model explainability.
💡 Core strengths:
- Predictive Modeling (Classification & Regression)
- Data Analysis & Insight Generation
- Explainable AI (SHAP)
- Model Deployment (Streamlit, APIs)
A machine learning system that predicts heart disease risk and explains predictions using SHAP.
Heart disease remains a leading cause of death. Early risk prediction can significantly improve outcomes.
Built an XGBoost-based predictive model with SHAP explainability to provide interpretable health risk insights.
- Python, Pandas, NumPy
- Scikit-learn, XGBoost
- SHAP (Explainable AI)
- Streamlit (Deployment)
- Real-time heart risk prediction
- Feature importance visualization
- Interpretable model decisions
- Helps identify high-risk patients early
- Supports data-driven healthcare decisions
- Live App: [Cardio Ai]
- GitHub: [Add repo link]
- Detects anomalous transactions using ML
- Focus on precision, recall & imbalance handling
- Predicts customer churn for SaaS/businesses
- Helps improve retention strategies
- Scikit-learn, XGBoost
- TensorFlow, PyTorch
- Pandas, NumPy
- Matplotlib, Seaborn, Plotly
- Streamlit
- FastAPI
- Git & GitHub
- SHAP
- LIME
✔️ Build predictive ML models
✔️ Analyze and extract insights from data
✔️ Deploy ML systems (Streamlit / APIs)
✔️ Add explainability to AI models
I’m open to:
- Remote Data Science roles
- Machine Learning Engineering roles
- Freelance / contract projects
📩 Let’s work together on solving real-world problems using data.