The paper introduces ANCHOR, a category‑anchored framework that improves next point‑of‑interest (POI) recommendation by first estimating category‑level mobility intent and then grounding this intent into a candidate set using category anchors, historical visit memory, and user preferences. A history‑aware reranker selects the final POI by matching candidates with the user’s past mobility patterns and current context. Experiments on three real‑world check‑in datasets demonstrate that ANCHOR consistently outperforms traditional, structure‑enhanced, and LLM‑based baselines, while offering favorable trade‑offs among candidate coverage, ranking quality, and inference efficiency.
By Lexi Bai, Xiaopeng Zeng, Xun Zhou, Yuanshao Zhu, James Jianqiao Yu
BehaveRec is a three-signal framework that combines a causal session transformer, a bidirectional User History Encoder over a 90‑day window, and a GraphSAGE module built from behavioral embedding similarity. On an industrial dataset of 137M sequences, it improves R@5 by +3.2% over SASRec, and its advantage grows with user history length, becoming significant for users with 101+ interactions. The study also establishes a practical deployment rule of roughly 20 interactions per user for when long‑term history and behavioral‑graph signals are worthwhile.
By Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Selene Xu, Kaushiki Nag, Jianpeng Xu, Sushant Kumar
arXiv:2610.34790v1 Announce Type: new
Abstract: User memory helps personalized systems build on their understanding of users over time. In e-commerce, users convey their preferences and needs through...
By Sizhe Wang, Xinghao Fang, Rui Qiu, Zhenjia Ma, Dagui Chen, Kun Kuang, Hongcheng Guo
arXiv:2601. 21149v3 Announce Type: replace-cross Abstract: Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates.
By Maria Despoina Siampou, Shushman Choudhury, Shang-Ling Hsu, Neha Arora, Cyrus Shahabi
The paper introduces Nomad, a transfer-and-ground framework for generating human mobility trajectories without target-city trajectory data. It learns relative transitions from source cities using POI attributes and then grounds these transitions onto a target city’s POI map via a behavior graph and exploration–return walk. Experiments across ten cities show Nomad improves trajectory fidelity and downstream utility by roughly 15% and 3% respectively over adaptation baselines.
By Yidi Wang, Yunhe Zhang, Bangchao Deng, Dingqi Yang, Pengyang Wang
MotiveMob is a motivation-driven autoregressive framework for generating human mobility trajectories. It models the "why-where-when" decision process by first predicting a plausible motivation for each movement step and then jointly generating the next location and arrival time. The approach is evaluated under user-level and temporal distribution shifts, including seasonal changes and COVID-19 disruptions, and consistently outperforms pretraining- and prompting-based baselines in distributional fidelity.
By Mengkun Gao, Zengqing Wu, Renhe Jiang, Jiawei Wang, Yusong Wang, Chuang Yang, Shuyuan Zheng, Makoto Onizuka, Chuan Xiao