Identify Optimal Pedestrian Flow Forecasting Methods in Great Britain Retail Areas: A Comparative Study of Time Series Forecasting on Footfall Dataset

The UK retail landscape has undergone significant changes over the past decade, driven by factors such as the rise of online shopping, economic downturns, and, more recently, the COVID-19 pandemic. Accurately measuring pedestrian flows in retail areas with high spatial and temporal resolution is essential for selecting the most suitable forecast model for different retail locations. However, several studies have adopted a one-solution-fits-all approach, overseeing important local characteristics only sometimes captured by the best global model. In this work, we investigate the optimal forecasting method to predict pedestrian footfall in diverse retail areas in Great Britain. After reviewing six representative time series forecasting models, our results indicate that the LSTM model outperforms traditional methods in most areas. However, pedestrian counts at certain locations with particular spatial characteristics are better forecasted with other algorithms.