Online prediction of network-level public transport demand based on principle component analysis

Online demand prediction plays an important role in transport network services from operations, controls to management, and information provision. However, the online prediction models are impacted by streaming data quality issues with noise measurements and missing data. To address these, we develop a robust prediction method for online network-level demand prediction in public transport. It consists of a PCA method to extract eigen demand images and an optimization-based pattern recognition model to predict the weights of eigen demand images by making use of the partially observed real-time data up to the prediction time in a day. The prediction model is robust to data quality issues given that the eigen demand images are stable and the predicted weights of them are optimized using the network level data (less impacted by local data quality issues). In the case study, we validate the accuracy and transferability of the model by comparing it with benchmark models and evaluate the robustness in tolerating data quality issues of the proposed model. The experimental results demonstrate that the proposed Pattern Recognition Prediction based on PCA (PRP-PCA) consistently outperforms other benchmark models in accuracy and transferability. Moreover, the model shows high robustness in accommodating data quality issues. For example, the PRP-PCA model is robust to missing data up to 50% regardless of the noise level. We also discuss the hidden patterns behind the network level demand. The visualization analysis shows that eigen demand images are significantly connected to the network structure and station activity variabilities. Though the demand changes dramatically before and after the pandemic, the eigen demand images are consistent over time in Stockholm.