STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction

TL;DR

This paper presents STEF-DHNet, a deep hybrid neural network that effectively incorporates external factors like weather and time into long-term taxi demand prediction, outperforming existing methods and maintaining accuracy over extended periods.

Contribution

The paper introduces STEF-DHNet, a novel deep learning model combining CNN and LSTM to integrate external spatiotemporal factors for improved long-term demand forecasting.

Findings

Outperforms state-of-the-art methods on three datasets

Maintains high accuracy over long periods without retraining

Effectively integrates external factors into demand prediction

Abstract

Accurately predicting the demand for ride-hailing services can result in significant benefits such as more effective surge pricing strategies, improved driver positioning, and enhanced customer service. By understanding the demand fluctuations, companies can anticipate and respond to consumer requirements more efficiently, leading to increased efficiency and revenue. However, forecasting demand in a particular region can be challenging, as it is influenced by several external factors, such as time of day, weather conditions, and location. Thus, understanding and evaluating these factors is essential for predicting consumer behavior and adapting to their needs effectively. Grid-based deep learning approaches have proven effective in predicting regional taxi demand. However, these models have limitations in integrating external factors in their spatiotemporal complexity and maintaining high accuracy over extended time horizons without continuous retraining, which makes them less suitable for practical and commercial applications. To address these limitations, this paper introduces STEF-DHNet, a demand prediction model that combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to integrate external features as spatiotemporal information and capture their influence on ride-hailing demand. The proposed model is evaluated using a long-term performance metric called the rolling error, which assesses its ability to maintain high accuracy over long periods without retraining. The results show that STEF-DHNet outperforms existing state-of-the-art methods on three diverse datasets, demonstrating its potential for practical use in real-world scenarios.