基于Theano的下一个位置预测_Python_下载.zip

# Point-of-Interest Recommendation ## Datasets The datasets are from the work "Quan Yuan, Gao Cong, Zongyang Ma, Aixin Sun, Nadia Magnenat-Thalmann: Time-aware point-of-interest recommendation. SIGIR 2013.", and can be downloaded from [this link](http://www.ntu.edu.sg/home/gaocong/datacode.htm) : - Foursquare - Gowalla ## Realized models - **BPR** - **GRU** - **FPMC-LR:** *Yang, Rui, Run Zhao, and Dong Wang. "Successive Point-of-Interest Recommendation in Intelligent Business Area." (2015).* - **PRME:** *Feng, Shanshan, et al. "Personalized Ranking Metric Embedding for Next New POI Recommendation." IJCAI. Vol. 15. 2015.* - **Poi2Vec:** *Feng, Shanshan, et al. "POI2Vec: Geographical Latent Representation for Predicting Future Visitors." AAAI. 2017.* - (Unmodified) **GEOIE:** *Wang, Hao, et al. "Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation." IJCAI. 2018.* - **Distance2Pre:** *Q Cui, Y Tang, S Wu, L Wang. "Distance2Pre: Predict the Next Point-of-Interest via Mining Personalized Spatial Preference". 2019.* ## Usage 1. Download datasets to `./poidata/Foursquare` or `./poidata/Gowalla` respectively 2. Run the file `./poidata/extract_whole_user_buys.py` to extract poi sequences 3. Run the file `prog_xxx.py`to train specific model.