PlanWise: An Explainable AI for Multiclass Transportation Mode Prediction

<p>This work introduces <strong>PlanWise</strong>, an explainable AI (XAI) framework for multiclass transportation mode prediction. Daily travel decisions are influenced by multiple factors such as cost, comfort, safety, weather, and time, often leading to uncertainty. PlanWise leverages machine learning classifiers — Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and XGBoost — to predict the most suitable mode of transport among Cab, Family, or Bus options. To enhance trust and interpretability, SHAP (SHapley Additive exPlanations) is integrated for both global and local model explanations. Experimental results show that XGBoost consistently achieves the highest predictive performance, while Decision Tree offers strong interpretability with competitive results. Feature importance analysis reveals that <strong>Cost, Day Type, and Travel Time</strong> are the most influential factors shaping decisions. This framework demonstrates the potential of explainable AI in urban mobility, helping commuters make informed choices while providing actionable insights for transport planners and policymakers.</p>