Travel time and ridership growth are two indicators of how interconnectivity affects the effectiveness of public transportation. Using a comparison of Extreme Gradient Boosting, polynomial regression (Degree 2), and the semi-linear regression approach, this research report attempts to determine the impact of interconnectivity and identify the most effective technique for estimating ridership demand for multi-modal transport systems. The influence of several factors on ridership demand is evaluated in three cities where the metro and bus rapid transit system (BRTS) are operational. The results show that ridership is impacted by interconnectedness. The metro-BRTS transfer sites and the number of boardings in Ahmedabad show a strong correlation, indicating well-established multimodal integration (R2 = 0.974). According to Jaipur, route length was the most important feature, indicating that transfers are more efficient over longer routes with fewer interchanges. Pune showed moderate predictability, indicating changes in intermodal connections and increased variability in passenger behaviour. The SHAP (Shapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) analyses found that the number of interchange locations and metro alighting volumes had the greatest positive impact on BRTS ridership. However, long travel times and frequent stops discourage ridership and deter commuters.
Dudhe et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: