Fusing Geographic Information Into Latent Factor Model for Pick-Up Region Recommendation

Taxis' trajectories increasingly become an important data source for pick-up regions recommendation. However, long-term and growing taxi trajectory data would inevitably reduce the efficiency of recommendation and consume huge amounts of storage resources. Therefore, a Latent Factor Model integrated with the geographic information, the GeoLFM, is put forward for solving the data sparseness problem caused by the short-term taxis' trajectories. This model makes up the faultiness of data sparseness by integrating the geographic information being related to drivers into the decomposition of matrix. With the comparison between our experimental method and others, the Mean Absolute Error (MAE) between the recommended results and actual values is reduced by 23.4%, while the Root Mean Square Error (RMSE) is lowered by 19.8%.

[1]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[2]  Feng Xia,et al.  Time-Location-Relationship Combined Service Recommendation Based on Taxi Trajectory Data , 2017, IEEE Transactions on Industrial Informatics.

[3]  Jinjun Chen,et al.  Recommending a personalized sequence of pick-up points , 2018, J. Comput. Sci..

[4]  Xing Xie,et al.  An Interactive-Voting Based Map Matching Algorithm , 2010, 2010 Eleventh International Conference on Mobile Data Management.

[5]  Jiye Liang,et al.  A fusion probability matrix factorization framework for link prediction , 2018, Knowl. Based Syst..

[6]  Chien-Liang Liu,et al.  Large-scale recommender system with compact latent factor model , 2016, Expert Syst. Appl..

[7]  Ioannis Konstas,et al.  On social networks and collaborative recommendation , 2009, SIGIR.

[8]  Zhang Hui,et al.  Research on taxi drivers' passenger hotspot selecting patterns based on GPS data: A case study in Wuhan , 2017, 2017 4th International Conference on Transportation Information and Safety (ICTIS).

[9]  Xing Xie,et al.  Where to find my next passenger , 2011, UbiComp '11.

[10]  Hang Li,et al.  Spatial–temporal travel pattern mining using massive taxi trajectory data , 2018, Physica A: Statistical Mechanics and its Applications.

[11]  Yu Zheng,et al.  Travel time estimation of a path using sparse trajectories , 2014, KDD.

[12]  Lin Zhang,et al.  A multi-period analysis of taxi drivers' behaviors based on GPS trajectories , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[13]  Victor C. S. Lee,et al.  TaxiRec: Recommending Road Clusters to Taxi Drivers Using Ranking-Based Extreme Learning Machines , 2015, IEEE Transactions on Knowledge and Data Engineering.

[14]  Tao Pei,et al.  Integrating spatial and temporal contexts into a factorization model for POI recommendation , 2018, Int. J. Geogr. Inf. Sci..

[15]  Xing Xie,et al.  GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation , 2014, KDD.

[16]  Yunpeng Wang,et al.  Mining factors affecting taxi drivers’ incomes using GPS trajectories , 2017 .

[17]  Lin Sun,et al.  Understanding Taxi Service Strategies From Taxi GPS Traces , 2015, IEEE Transactions on Intelligent Transportation Systems.

[18]  Huan Liu,et al.  Content-Aware Point of Interest Recommendation on Location-Based Social Networks , 2015, AAAI.