AI-Powered Evaluation of On-Demand Public Transport: A Hybrid Simulation Approach

On-demand public transport systems are increasingly adopted to improve service flexibility, reduce operating costs, and meet emerging mobility needs. Evaluating their performance under realistic demand and operational conditions, however, remains a complex challenge. This study presents a hybrid simulation framework that integrates deep learning-based demand forecasting, behavioural survey data, and agent-based simulation to assess system performance. A BiLSTM neural network trained on real-world smartcard data forecasts short-term passenger demand, which is embedded into an agent-based model simulating vehicle dispatch, routing, and passenger interactions. The framework is applied to a case study in Melbourne, Australia, comparing a baseline fixed-route service with two on-demand scenarios. Results show that the most flexible scenario reduces the average passenger trip time by 32%, decreases the average wait time by 34%, increases vehicle occupancy from 12.1 to 18.6 passengers per vehicle, lowers emissions per passenger trip by 72%, and cuts the service cost per trip from AUD 6.82 to AUD 4.73. These findings demonstrate the potential of hybrid on-demand services to improve operational efficiency, passenger experience, and environmental outcomes. The study presents a novel, integrated methodology for scenario-based evaluation of on-demand public transportation using real-world transportation data.