Modelling and Forecasting Bus Passenger Demand using Time Series Method

Abstract

Public bus transport demand modelling and forecasting is important for decision-making, transport policy formulation, urban public transport planning and allocation of buses into the network. It is the key to the solutions for major transportation problems. In this paper, a univariate time series ARIMA model is used to forecast the inter-district public transport travel demand from Trivandrum to five other districts of Kerala. The data used in the study is a part of the transaction on ticket sales by Kerala State Road Transport Corporation (KSRTC) maintained at the Trivandrum central depot for the period between 2010 and 2013. ARIMA model is developed to predict the travel demand between the five district pairs and the demand is forecasted for future. The accuracy of the developed ARIMA model is demonstrated in the study by comparing the forecasted values with the actual demand observed in 2013. The results show that time series ARIMA model, which uses only historical data of passenger demand is accurate for zones which are dependent on each other and for short-term demand forecasting. � 2018 IEEE.