TS-Mob framework enhances time series models for human mobility prediction

Researchers have developed TS-Mob, a new framework designed to improve time series foundation models for predicting human mobility. This framework integrates geographic and social signals, computed from open data like population density and Points of Interest, alongside weather data. When applied to the TimesFM model, TS-Mob demonstrated significant performance improvements over existing methods on benchmarks including Bike New York City, Taxi Beijing, and a Spanish origin-destination matrix, showing reduced error rates and increased predictive accuracy. AI

IMPACT This framework could improve urban planning and transportation systems by providing more accurate human mobility predictions.

RANK_REASON The cluster contains an arXiv preprint detailing a new framework and model for time series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Bike New York City
• Hugging Face
• Massimiliano Luca
• Spain
• Taxi Beijing
• TimesFM
• TS-Mob

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →