Far Out: Predicting Long-Term Human Mobility

• DOI: 10.1609/aaai.v26i1.8212
• Publication Date: 2022-06-01T20:52:52Z
• Authors: Adam Sadilek; John Krumm
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Much work has been done on predicting where is one going to be in the immediate future, typically within next hour. By contrast, we address open problem of human mobility far into a scale months and years. We propose an efficient nonparametric method that extracts significant robust patterns location data, learns their associations with contextual features (such as day week), subsequently leverages this information predict most likely at any given time future. The entire process formulated principled way eigendecomposition problem. Evaluation massive dataset more than 32,000 days worth GPS data across 703 diverse subjects shows our model predicts correct high accuracy, even years This result opens number interesting avenues for future research applications.