A Machine Learning Approach to adjust ridership computed from Wi-Fi data in Public Transport

Abstract

Wi-Fi data, collected from sensors placed on buses, seem promising for generating O-D matrices over a network. However, obtaining accurate bus ridership data is a challenge for public transport operators. Issues of completeness remain, as Wi-Fi sensors do not detect all signals emitted by connected objects in their vicinity, and some people do not own these devices. Data scaling is therefore a crucial step in the process of building O-D matrices from Wi-Fi data. In this work, four machine learning algorithms are compared to estimate the absolute values of passengers boarding and alighting at a bus stop based on Wi-Fi data and spatial and temporal characteristics. The results show that LGBM is the most relevant algorithm for generating accurate data.