Short-term passenger demand modelling using automatic fare collection data: a case study of Hubli-Dharwad BRTS

A well-planned Intelligent Transport System (ITS), is the need of the hour for solving the problem of excessive traffic and unacceptable travel durations in public transit systems. However, for the successful operation of an ITS, the forecasting of passenger demand on a regular basis is essential. Obtaining reliable and accurate passenger data required for forecasting passenger demand is a genuinely tedious task for most of the researchers. The current study focused on short-term forecasting of passenger demand using reliable ITS-based data from Hubli-Dharwad Bus Rapid Transit System (HDBRTS) as a case study. The aggregate pattern of passenger demand data was visualized using one month of Automated Fare Collection System (AFCS) data. Subsequently, Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA models were used on the data of selected stations and tested for their forecasting accuracy. Outcomes of the current case study show that Seasonal ARIMA models are the most suitable for forecasting the passenger data over the conventional ARIMA models. The most suitable and reliant models were evidenced through lower values of Mean Absolute Percentage Error (MAPE), Akaike’s Information Criterion (AIC), and Bayesian Information Criterion (BIC). The current case study helps in having an inclusive view of the passenger flow characteristics for the further advancement of the system. Research work in the Indian context, especially on the usage of AFCS data, is quite limited, this study makes to explore the possibility of using AFCS data efficiently in forecasting passenger demand.