Our Work

A Framework for Auditing Multilevel Models using Explainability Methods

An audit framework for assessing technical aspects of regression MLMs, emphasizing transparency and explainability, with comparisons of popular explainability methods.

AI Governance and Compliance Challenges

Exploring the challenges and solutions in AI governance and compliance, with a focus on the APPRAISE framework.

An Audit Framework for Technical Assessment of Binary Classifiers

This paper introduces an audit framework for assessing binary classifiers, ensuring compliance with the AIA by evaluating model transparency and fairness.

Quantifying Popularity Bias in Recommender Systems

Quantifying biases in Recommender Systems, proposing metrics to address fairness, demonstrated effectiveness on diverse datasets.