1) 概率模型
2）路径概率
3）定义当前访问点之前确定时间段内，访问过的地方到当前点点访问概率。
4）区域划分（binary tree，一个location可被划分到多个region）
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| POI2Vec: Geographical Latent Representation for Predicting Future Visitors | |||||||||||
| 文献作者 | Shanshan Feng, Gao Cong, Bo An, Yeow Meng Chee | ||||||||||
| 文献发表年限 | 2017 | ||||||||||
| 文献关键字 | |||||||||||
| Future Visitor Prediction, Sequential Recommendation, binary tree, Probability Estimation | |||||||||||
| 摘要描述 | |||||||||||
| With the increasing popularity of location-aware social me- dia applications, Point-of-Interest (POI) recommendation has recently been extensively studied. However, most of the exist- ing studies explore from the users’ perspective, namely rec- ommending POIs for users. In contrast, we consider a new re- search problem of predicting users who will visit a given POI in a given future period. The challenge of the problem lies in the difficulty to effectively learn POI sequential transition and user preference, and integrate them for prediction. In this work, we propose a new latent representation model POI2Vec that is able to incorporate the geographical influence, which has been shown to be very important in modeling user mobil- ity behavior. Note that existing representation models fail to incorporate the geographical influence. We further propose a method to jointly model the user preference and POI sequen- tial transition influence for predicting potential visitors for a given POI. We conduct experiments on 2 real-world datasets to demonstrate the superiority of our proposed approach over the state-of-the-art algorithms for both next POI prediction and future user prediction. | |||||||||||
