Learning from Hometown and Current City: Cross-city POI Recommendation via Interest Drift and ...
summary
Proposes PR-UIDT, a matrix-factorization framework that splits each user vector into a city-independent part and a city-dependent part and represents each POI with separate vectors for locals and travelers; implements both square-error and ranking-loss variants and evaluates on three real-world datasets (Tencent WeChat: Beijing, Shanghai, Tianjin; Yelp). Claims to reduce cross-city sparsity and improve recommendation accuracy with interest drift and transfer modeling, showing 0.4%–20.5% relative gains and consistent multi-city results.
AI-written summary · about
related talks
06mPREFER: Point-of-interest REcommendation with efficiency and privacy-preservation via Federated ...
32mLet's talk about Recommendation Systems!
35mHybrid Recommender Systems in Python
16mMaking recommendations explainable
46mDiversification in Recommender Systems
28m"Where, When, Why, and How: Directi
42mShould we stop using distance in our location-based data recommendation models?
22mExploiting Auxiliary Information for Better Recommendation