Fig. 6: Correlation-based importance ranking and SHAP explanations.
From: A causal discovery and inference framework for on-demand food delivery delays
a Presents the relative feature-importance ranking from the correlation-based predictive model, interpreted as each variable’s relative contribution to predicted delays. b Shows SHAP beeswarm diagrams, where each point corresponds to an order-level SHAP value; the x-axis is the SHAP contribution to predicted delay, and color encodes the feature value from low to high.
