Collective Prediction of Individual Mobility Traces with Exponential Weights
This incremental improvement addresses mobility prediction for applications like urban planning or traffic management.
The paper tackles short-term human mobility prediction by pairing the Exponential Weights forecaster with a large ensemble of experts derived from 10 million mobile phone users, achieving significantly higher average accuracy than individual constant order Markov models.
We present and test a sequential learning algorithm for the short-term prediction of human mobility. This novel approach pairs the Exponential Weights forecaster with a very large ensemble of experts. The experts are individual sequence prediction algorithms constructed from the mobility traces of 10 million roaming mobile phone users in a European country. Average prediction accuracy is significantly higher than that of individual sequence prediction algorithms, namely constant order Markov models derived from the user's own data, that have been shown to achieve high accuracy in previous studies of human mobility prediction. The algorithm uses only time stamped location data, and accuracy depends on the completeness of the expert ensemble, which should contain redundant records of typical mobility patterns. The proposed algorithm is applicable to the prediction of any sufficiently large dataset of sequences.