BiasLens

BiasLens is one of the projects that best represents how I combine technical work with broader decision-making impact. I wanted to make bias detection more visible, interpretable, and actionable.

what I did

1. 01AI built a Streamlit app using Python, Fairlearn, and scikit-learn to audit algorithmic bias in datasets with 10,000+ records.
2. 02AI evaluated fairness metrics such as Demographic Parity and Equal Opportunity.
3. 03AI tested mitigation strategies including reweighing and threshold adjustment to improve fairness outcomes.
4. 04AWhat interested me most was translating model-risk concepts into something decision-makers could actually interpret and use.

built with