Explainable AI for Transparent Decision-Making: A Quantitative Study on Interpretable Machine Learning Models

Abstract

Artificial Intelligence (AI) systems are increasingly used in critical decision-making domains such as healthcare, finance, and criminal justice. However, the black-box nature of many advanced machine learning models raises concerns regarding transparency, trust, and accountability. Explainable Artificial Intelligence (XAI) aims to address these challenges by providing interpretable insights into model behavior and decision-making processes. This study presents a quantitative evaluation of explainable AI techniques applied to predictive models, comparing their performance, interpretability, and user trust. Using benchmark datasets, traditional black-box models are compared with interpretable models and post-hoc explanation techniques. Statistical analysis demonstrates that explainable models significantly improve user understanding and trust while maintaining competitive predictive accuracy. The findings highlight the importance of integrating explainability into AI systems to ensure ethical, transparent, and reliable decision-making.