GeoFormer: Predicting Human Mobility using Generative Pre-trained Transformer (GPT)
This work addresses human mobility prediction for applications like disaster planning and epidemic control, but it is incremental as it adapts an existing GPT architecture to a specific domain.
The paper tackles the problem of predicting human mobility by proposing GeoFormer, a decoder-only transformer model adapted from GPT, which achieved top-3 ranking in the HuMob Challenge 2023, performing well on GEO-BLEU and DTW metrics using datasets of 25,000 and 100,000 individuals over 75 days.
Predicting human mobility holds significant practical value, with applications ranging from enhancing disaster risk planning to simulating epidemic spread. In this paper, we present the GeoFormer, a decoder-only transformer model adapted from the GPT architecture to forecast human mobility. Our proposed model is rigorously tested in the context of the HuMob Challenge 2023 -- a competition designed to evaluate the performance of prediction models on standardized datasets to predict human mobility. The challenge leverages two datasets encompassing urban-scale data of 25,000 and 100,000 individuals over a longitudinal period of 75 days. GeoFormer stands out as a top performer in the competition, securing a place in the top-3 ranking. Its success is underscored by performing well on both performance metrics chosen for the competition -- the GEO-BLEU and the Dynamic Time Warping (DTW) measures. The performance of the GeoFormer on the HuMob Challenge 2023 underscores its potential to make substantial contributions to the field of human mobility prediction, with far-reaching implications for disaster preparedness, epidemic control, and beyond.