Robust Real-Time Delay Predictions in a Network of High-Frequency Urban Buses
||Robust Real-Time Delay Predictions in a Network of High-Frequency Urban Buses|
||Mattias Villani <email@example.com>|
||2021-04-16 – 2021-06-01|
Providing transport users and operators with accurate forecasts on travel times is challenging due to a highly stochastic traffic environment. Public transport users are particularly sensitive to unexpected waiting times, which negatively affect their perception on the system’s reliability. The project develops a robust model for real-time bus travel time prediction that depart from Gaussian assumptions by using Student-t errors. The proposed approach uses spatiotemporal characteristics from the route and previous bus trips to model short-term effects, and date/time variables and Gaussian process priors for long-run forecasts. The model allows for flexible modeling of mean, variance and kurtosis spaces. We propose algorithms for Bayesian inference and probabilistic forecast distributions. Experiments are performed using data from high-frequency buses in Stockholm, Sweden.