Enhancing Machine Learning Model Using Explainable AI

This paper implements Explainable Artificial Intelligence (XAI) techniques, specifically LIME and SHAP, in a hotel review management model. The goal is to enhance transparency, interpretability, and trustworthiness. LIME provides local explanations, highlighting the important features that influenced individual predictions. SHAP offers a global perspective on feature importance, helping users understand the overall impact of each feature on the model’s predictions. By integrating XAI, the model becomes more transparent, enabling users to comprehend the decision-making process, validate decisions, identify biases, and make informed decisions based on reliable insights from the reviews.