Clustering and Forecasting Urban Bus Passenger Demand with a Combination of Time Series Models

The present paper focuses on the analysis of large data sets from public transport networks, more specifically, on how to predict urban bus passenger demand. A series of steps are proposed to ease the understanding of passenger demand. First, given the large number of stops in the bus network, these are divided into clusters and then different models are fitted for a representative of each of the clusters. The aim is to compare and combine the predictions associated with traditional methods, such as exponential smoothing or ARIMA, with machine learning methods, such as support vector machines or artificial neural networks. Moreover, support vector machine predictions are improved by incorporating explanatory variables with temporal structure and moving averages. Finally, through cointegration techniques, the results obtained for the representative of each group are extrapolated to the rest of the series within the same cluster. A case study in the city of Salamanca (Spain) is presented to illustrate the problem.