Proposing a Model for Predicting Passenger Origin-Destination in Online Taxi-Hailing Systems

TL;DR

This paper introduces a predictive model for passenger origin-destination flows in online taxi-hailing systems, combining clustering, matrix factorization, and neural networks to improve accuracy in short-term travel demand forecasting.

Contribution

The study presents a novel integrated approach using clustering, matrix factorization, and stacked RNNs for origin-destination prediction in taxi systems, outperforming existing models.

Findings

Achieves 5-7% lower MAPE for 1-hour windows

Achieves 14% lower MAPE for 30-minute windows

Demonstrates improved accuracy over existing models

Abstract

Due to the significance of transportation planning, traffic management, and dispatch optimization, predicting passenger origin-destination has emerged as a crucial requirement for intelligent transportation systems management. In this study, we present a model designed to forecast the origin and destination of travels within a specified time window. To derive meaningful travel flows, we employ K-means clustering in a four-dimensional space with a maximum cluster size constraint for origin and destination zones. Given the large number of clusters, we utilize non-negative matrix factorization to reduce the number of travel clusters. Furthermore, we implement a stacked recurrent neural network model to predict the travel count in each cluster. A comparison of our results with existing models reveals that our proposed model achieves a 5-7\% lower mean absolute percentage error (MAPE) for 1-hour time windows and a 14\% lower MAPE for 30-minute time windows.