#xgboost

End-to-end Employee Attrition Prediction system with data analysis, feature engineering, model comparison, explainable AI (SHAP), FastAPI deployment, and Docker.

Full-stack SaaS product analytics platform: executive KPIs, product analytics, ML customer segmentation, XGBoost churn prediction, and a Gemini-powered AI analyst copilot. Encore.ts + Next.js + Python/scikit-learn/XGBoost.

Reactive AI Agent for Fraud Detection

Empirical study: do LLM-generated features improve tabular ML models? 10 LLMs, 3 datasets, 3 algorithms, 219 experiments.

AI-powered agricultural demand and supply forecasting system using LSTM, XGBoost, and Streamlit with crop recommendation.

Explainable machine learning workflows for clinical risk prediction using healthcare data, ensemble models, validation techniques, and interpretable AI methods in Python.

Agentic AI workforce forecasting system using Streamlit, Flask, CrewAI-style agents, LangGraph-style workflow logic, guardrails, and VET/VTO staffing recommendations.

🐝 State-of-the-art Python AutoML metaframework — fuses GenAI (built on Firefly Agentic / Pydantic AI) with classical ML & Deep Learning. Hexagonal, secure-by-default, governed.