Application of multi-class machine learning algorithms to predicting commuter preference & system benefits of an integrated public transport: The case of a proposed dedicated bus lane system

• Explored user preference and benefit of a planned dedicated bus lane PT system (DBLPT) • The MCMLC models revealed that all the classifiers are stable and consistent in terms prediction accuracy • Bus_Minibus system was predicted as the most preferred DBLPT system followed by Bus_Three-wheeler • AHP results revealed that Bus_Minibus commuters placed high value on transport fare, while Bus_3w commuters prioritized both in and out of vehicle travel time • Bus_Minibus system was predicted to generate the highest daily revenue and passenger ridership In contrast to most industrialized countries, the majority of Sub-Saharan African cities continue to struggle with the growing demand for public transport (PT). Freetown, Republic of Sierra Leone, was exploring proposals to implement the first dedicated bus lane PT system (DBLPT) with high-quality buses on selected corridors. This study attempts to explore user preference for the planned DBLPT system and its benefits in terms of revenue and passenger ridership. The system was analyzed using four hypothetical PT scenarios of system replacement and integration: Bus Only, Bus_Minibus, Bus_Three-wheeler, and Bus_Private car. Onboard vehicle traffic and revealed preference data were collected for designing the stated preference survey that was distributed to 1,500 respondents (4,500 observations). Travel time, waiting time, transport fare, and other trip and sociodemographic attributes varied across the PT scenarios. Fourteen multi-class machine learning classifiers (MCMLC) were trained to analyze each scenario. Further, the Analytical Hierarchy Process (AHP) and Sankey Diagrams were used to rank and visualize the most significant attributes. The findings revealed that all classifiers are consistent in terms of prediction accuracy. Bus_Minibus system was predicted as the most preferred DBLPT system, followed by Bus_Three-wheeler. Commuters who preferred the Bus_Minibus DBLPT system placed a high value on transport fare, while Bus_Three-wheeler commuters prioritized both in and out-of-vehicle travel time. Additionally, the Bus_Minibus system was predicted to generate the highest daily revenue and passenger ridership, followed by the Bus_Three-wheeler system. These findings and other model results underscore the preference for and benefits of an integrated DBLPT system.