Learning robust travel preferences via check-in masking for next POI recommendation

Chenghua Duan, Junhao Wen, Wei Zhou, Jun Zeng, Yihao Zhang

Abstract: Highlights•A stochastic context masking strategy to aid in modeling robust travel preferences.•We find learning robust preferences can enhance the model’s resilience to noise.•We exploit geospatial indexing to alleviate the data sparsity issue.•We consider users’ living areas to balance masking and information loss.