Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning

TLDR

Recent literature on short‑term traffic flow forecasting has expanded, yet differing datasets and evaluation metrics make it hard to compare model advantages and limitations. This study reviews short‑term traffic flow forecasting methods within a probabilistic graphical model framework and introduces two seasonality‑aware support vector regression models. The authors conduct an extensive experimental comparison on a publicly available dataset, establishing a common baseline, and develop two SVR models that exploit traffic flow seasonality for efficient prediction. Results show that a SARIMA model with a Kalman filter achieves the highest accuracy, while the proposed seasonal SVR remains highly competitive during peak congestion.

Abstract

The literature on short-term traffic flow forecasting has undergone great development recently. Many works, describing a wide variety of different approaches, which very often share similar features and ideas, have been published. However, publications presenting new prediction algorithms usually employ different settings, data sets, and performance measurements, making it difficult to infer a clear picture of the advantages and limitations of each model. The aim of this paper is twofold. First, we review existing approaches to short-term traffic flow forecasting methods under the common view of probabilistic graphical models, presenting an extensive experimental comparison, which proposes a common baseline for their performance analysis and provides the infrastructure to operate on a publicly available data set. Second, we present two new support vector regression models, which are specifically devised to benefit from typical traffic flow seasonality and are shown to represent an interesting compromise between prediction accuracy and computational efficiency. The SARIMA model coupled with a Kalman filter is the most accurate model; however, the proposed seasonal support vector regressor turns out to be highly competitive when performing forecasts during the most congested periods.