Personal Data Science Projects

Assess fairness of machine learning models and choose an appropriate fairness metric for your use case with Fairlearn

Demos about Teaching your Models to play fair with FairLearn

Learn different techniques for mitigating fairness-related harms using Fairlearn.

An end-to-end MLOps pipeline for a production-grade fraud detection model. This project demonstrates best practices including data versioning (DVC), experiment tracking (MLflow), CI/CD (GitHub Actions), containerization (Docker), deployment on GKE, and advanced model analysis (poisoning attacks, drift, fairness, explainability).

Microsoft Ignite - Getting started on your health-tech journey using responsible AI

Demo's of FairLearn and InterpretML as described in my article on responsible AI.

AI-powered bias detection for datasets and ML models — with fairness metrics, natural language reports, and explainability tools.

Fairlearn Jupyter notebooks samples

🔬 Drop in any ML model → get SHAP explainability, fairness audit & drift detection in seconds

An ethically-aware deep learning project to predict credit card offer acceptance while mitigating income-based bias using SHAP, Fairlearn, and AIF360.

A platform developed with Cash App to help ML engineers detect and visualize biases in models using Fairlearn. Features include a collaborative and interactive dashboard (React, Chart.js), a Flask backend, and a secure MySQL database for data storage and analysis.

This repository was used for my thesis. The goal was to find a biased dataset, and mitigate its bias. That is done under the patients directory. Check the README file for more.

A comprehensive bias analysis on bank loan data, examining potential unfairness in credit quality predictions across age groups

Practical, implementation-ready AI governance framework aligned to NIST AI RMF — automated risk scoring, data lineage validation, bias detection, model cards, and a governance dashboard. Built for enterprise architects deploying AI in regulated environments.

Student Success Model (SSM)

Full-stack Data Science engine: Advanced SQL feature engineering, Customer Segmentation (K-Means), and LTV Prediction using Deep Learning (TensorFlow). Includes automated AI Ethics & Bias auditing.

Built a fairness-aware ML system for loan approval using Fairlearn and SHAP. Detected and reduced bias (DP & EO) across age groups while maintaining accuracy. Analyzed trade-offs between fairness and decision behavior, aligning results with responsible AI and EU regulatory principles.

Credit risk scoring model using XGBoost with fairness constraints implemented via Fairlearn to mitigate bias in financial decision making. Implemented on the Statlog (German Credit Data) dataset. Also includes the notebooks for the preprocessing and the hyper tuning of the dataset.

Investigation of gender bias in music recommender systems