Using Neural Nets to Predict Transportation Mode Choice: An Amsterdam Case Study
In the Amsterdam metropolitan area, the opening of a new metro line along the north south axis of the city has introduced a significant change in the region’s public transportation network. Mode choice analysis can help in assessment of changes in traveler behavior that occurred after the opening of the new metro line. As it is known that artificial neural nets excel at complex classification problems, this paper aims to investigate an approach where the traveler’s transportation mode is predicted from a choice set through a neural net. Although the approach shows promising results, it has been found that its performance can be attributed partly to the presence of differences in data patterns between the actual and generated trips, which the neural net is able to detect. By adding generated user characteristic attributes, the performance of the model can be boosted slightly overall, and significantly concerning prediction of whether or not a trip was made by car.
|Transportation mode choice, Artificial neural nets, Machine learning, Public transportation network change, Travel behaviour|
|Procedia Computer Science|
|International Conference on Ambient Systems, Networks and Technologies|
Buijs, R.J.W, Koch, T, & Dugundji, E.R. (2020). Using Neural Nets to Predict Transportation Mode Choice: An Amsterdam Case Study. In The 11th International Conference on Ambient Systems, Networks and Technologies (pp. 115–122). doi:10.1016/j.procs.2020.03.015