Enhancing Transparency and Trust in Machine Learning Models through Explainable AI (XAI)

Explainable Artificial Intelligence (XAI) aims to make the behaviour and decisions of machine learningmodels understandable to humans. This paper reviews current XAI methods, implements severaltechniques on a relevant case study, and evaluates their effectiveness in terms of interpretability andperformance trade-offs. The study demonstrates that XAI techniques such as LIME and SHAP can providemeaningful insights into complex models without substantially compromising their performance.