A comparative study of deep learning and ensemble learning to extend the horizon of traffic forecasting

2025-04-30

AI Summary

This paper addresses the challenging problem of 30-day long-term traffic flow forecasting. It systematically evaluates the modeling capabilities of deep learning models—including RNNs, Informer, and Transformer—and ensemble learning (XGBoost) on large-scale real-world road network data. The study reveals that success in long-term forecasting hinges less on capturing long-range temporal dependencies and more on accurately modeling periodic and event-driven patterns. To this end, the authors propose a novel time embedding mechanism that significantly enhances model awareness of seasonal and holiday-related temporal structures; remarkably, a plain RNN equipped with this mechanism outperforms Informer by 31.1% in 30-day forecasting. Furthermore, XGBoost achieves performance on par with state-of-the-art deep models using time features alone. The work also conducts systematic ablation studies on input length, temporal granularity, holiday encoding, and data scale, yielding new insights into traffic forecasting paradigms and establishing practical benchmarks for long-term prediction.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Traffic forecasting is vital for Intelligent Transportation Systems, for which Machine Learning (ML) methods have been extensively explored to develop data-driven Artificial Intelligence (AI) solutions. Recent research focuses on modelling spatial-temporal correlations for short-term traffic prediction, leaving the favourable long-term forecasting a challenging and open issue. This paper presents a comparative study on large-scale real-world signalized arterials and freeway traffic flow datasets, aiming to evaluate promising ML methods in the context of large forecasting horizons up to 30 days. Focusing on modelling capacity for temporal dynamics, we develop one ensemble ML method, eXtreme Gradient Boosting (XGBoost), and a range of Deep Learning (DL) methods, including Recurrent Neural Network (RNN)-based methods and the state-of-the-art Transformer-based method. Time embedding is leveraged to enhance their understanding of seasonality and event factors. Experimental results highlight that while the attention mechanism/Transformer framework is effective for capturing long-range dependencies in sequential data, as the forecasting horizon extends, the key to effective traffic forecasting gradually shifts from temporal dependency capturing to periodicity modelling. Time embedding is particularly effective in this context, helping naive RNN outperform Informer by 31.1% for 30-day-ahead forecasting. Meanwhile, as an efficient and robust model, XGBoost, while learning solely from time features, performs competitively with DL methods. Moreover, we investigate the impacts of various factors like input sequence length, holiday traffic, data granularity, and training data size. The findings offer valuable insights and serve as a reference for future long-term traffic forecasting research and the improvement of AI's corresponding learning capabilities.

Problem

• Compares deep learning and ensemble learning for long-term traffic forecasting
• Evaluates ML methods for forecasting horizons up to 30 days
• Investigates temporal dynamics and periodicity modeling in traffic prediction

Innovation

• XGBoost and DL methods for traffic forecasting
• Time embedding enhances seasonality understanding
• Transformer captures long-range dependencies effectively