Abstract
Learning the vector representing of Point Of Interest(POI) is a key aspect of POI recommender systems. As for shop POI embedding, in addition to the goods selling in shops, the location of shops is also an important factor that must be considered. Word2vec is a commonly used POI embedding model but it cannot be trained directly using location data. In this paper, we present a geohash based Place2vec model, geohash is a geocoding system that can encoding the location of shops in a string form, which can be treated as a spatial context of the Word2Vec model. We investigate the extent to which similar shops occur within the same products contexts and similar spatial contexts, and enrich a dataset of location, type and product lists of shops from YIWUGOU Online Shop Data1. The evaluation results shows that the shop vector trained by combined contexts outperform the vector trained by the products contexts.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
