Predicting Episodes of Non-Conformant Mobility in Indoor Environments.

Traditional mobility prediction literature focuses primarily on improved methods to extract latent patterns from individual-specific movement data. When such predictions are incorrect, we ascribe it to 'random' or 'unpredictable' changes in a user's movement behavior. Our hypothesis, however, is that such apparently-random deviations from daily movement patterns can, in fact, of ten be anticipated. In particular, we develop a methodology for predicting Likelihood of Future Non-Conformance (LFNC), based on two central hypotheses: (a) the likelihood of future deviations in movement behavior is positively correlated to the intensity of such trajectory deviations observed in the user's recent past, and (b) the likelihood of such future deviations increases if the user's strong-ties have also recently exhibited such non-conformant movement behavior. We use extensive longitudinal indoor location data (spanning 4+ months) from an urban university campus to validate these hypotheses, and then show that these features can be used to build an accurate non-conformance predictor: it can predict non-conformant mobility behavior two hours in advance with an AUC ≥ 0.85, significantly outperforming the baseline. We also show that this prediction methodology holds for a representative outdoor public-transport based mobility dataset. Finally, we use a real-world mobile crowd-sourcing application to show the practical impact of such non-conformance: failure to identify such likely anomalous movement behavior causes workers to suffer a noticeable drop in task completion rates and reduces the spatial spread of successfully completed tasks.