Abstract
This research paper provides a framework for the efficient representation and analysis of both spatial and temporal dimensions of panel data. This is achieved by representing the data as spatio-temporal image-matrix, and applied to a case study on forecasting public transport ridership. The relative performance of a subset of machine learning techniques is examined, focusing on Convo-lutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) neural networks. Furthermore Sequential CNN-LSTM, Parallel CNN-LSTM, Augmented Sequential CNN-LSTM are explored. All models are benchmarked against a Fixed Effects Ordinary Least Squares regression. Historical ridership data has been provided in the framework of a project focusing on the impact that the opening of a new metro line had on ridership. Results show that the forecasts produced by the Sequential CNN-LSTM model performed best and suggest that the proposed framework could be utilised in applications requiring accurate modelling of demand for public transport. The described augmentation process of Sequential CNN-LSTM could be used to introduce exogenous variables into the model, potentially making the model more explainable and robust in real-life settings.
1. Introduction
1.1. Problem statement and background
In the context of public transport, forecasting ridership is essential for business operations. Knowing the demand for travel allows public transport companies to make the transportation system more efficient, and helps to proactively improve the level of service for their customers and eliminate unnecessary costs [13, 1]. Having an effective model of how demand for public transport changes over time is important for future planning, introducing new routes, more efficient schedules, and optimising transportation operations (e.g. frequency of buses on a certain line) [3, 5].
6. Discussion
It appears that Sequential CNN-LSTM is the best model in terms of performance on the test set. Its score, however, is quite close to that of the suggested Augmented CNN-LSTM model. Moreover, in terms of convergence speed, the Sequential CNN-LSTM model is the fastest in terms of passes (epochs) required to fit the training set.
