Comparative Analysis of LSTM, ARIMA, and Facebook’s Prophet for Traffic Forecasting

Comparative Analysis of LSTM, ARIMA, and Facebook’s Prophet for Traffic Forecasting: Advancements, Challenges, and Limitations

Üzel, Ziyar (TU Delft Electrical Engineering, Mathematics and Computer Science)

Congeduti, E. (mentor)
Iosifidis, G. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2023-06-28

Accurate short-term traffic forecasting plays a crucial role in Intelligent Transportation Systems for effective traffic management and planning. In this study, the performances of three popular forecasting models are explored: Long Short-Term Memory (LSTM), Autoregressive Integrated Moving Average (ARIMA), and Facebook's Prophet, for short-term traffic prediction. The models were trained and evaluated using a dataset of traffic flow data collected from 161 detectors over a specific time period. The experimental results reveal that ARIMA outperformed LSTM and Prophet in terms of Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). This suggests that while deep learning methods, such as LSTM, are generally acknowledged to outperform ARIMA in short-term traffic forecasting, this study reveals that there are specific scenarios where such well-accepted fact needs to be tested.

time series analysis
Time Series Forecasting
traffic forecasting
LSTM
ARIMA
Prophet
Facebook
Meta
Intelligent Transport Systems

http://resolver.tudelft.nl/uuid:29fcfb96-3e96-4b11-93ec-217ba69ea412

Student theses

bachelor thesis

© 2023 Ziyar Üzel