Home Location Inference from Sparse and Noisy Data: Models and Applications

Accurate home location is increasingly important for urban computing. Existing methods either rely on continuous (and expensive) GPS data or suffer from poor accuracy. In particular, the sparse and noisy nature of social media data poses serious challenges in pinspointing where people live at scale. We revisit this research topic and infer home location within 100 by 100 meter squares at 70% accuracy for 71% and 76% of active users in New York City and the Bay Area, respectively. We believe this is the first time home location is detected at such a fine granularity using sparse and noisy data. Since people spend a large portion of their time at home, our model enables novel applications that were previously impossible. As a specific example, we focus on modeling people´s health at scale.