Human mobility is well described by closed-form gravity-like models learned automatically from data

TL;DR

This paper introduces simple, interpretable, machine-learned gravity-like models that predict human mobility flows more accurately than traditional gravity models and complex machine learning approaches, across various datasets and scales.

Contribution

It presents a novel approach to automatically learn closed-form, gravity-like models that outperform existing models in predicting human mobility.

Findings

Machine-learned models outperform gravity and deep learning models in accuracy.

Models are simple, interpretable, and applicable across datasets and scales.

Proposed models capture universal features of human mobility.

Abstract

Modeling of human mobility is critical to address questions in urban planning and transportation, as well as global challenges in sustainability, public health, and economic development. However, our understanding and ability to model mobility flows within and between urban areas are still incomplete. At one end of the modeling spectrum we have simple so-called gravity models, which are easy to interpret and provide modestly accurate predictions of mobility flows. At the other end, we have complex machine learning and deep learning models, with tens of features and thousands of parameters, which predict mobility more accurately than gravity models at the cost of not being interpretable and not providing insight on human behavior. Here, we show that simple machine-learned, closed-form models of mobility are able to predict mobility flows more accurately, overall, than either gravity or complex machine and deep learning models. At the same time, these models are simple and gravity-like, and can be interpreted in terms similar to standard gravity models. Furthermore, these models work for different datasets and at different scales, suggesting that they may capture the fundamental universal features of human mobility.