Foursquare Location-Content-Aware Recommender System

Foursquare uses its unique location technology and foot traffic panel to produce personalized recommendations of spatial items such as restaurants. Recently I've read a paper LCARS: A Spatial Item Recommender System that I implemented from scratch in R.

The recommender system combines the querying user's interest and the local preference of the querying city. Specifically, the generative model uses collapsed Gibbs sampling to learn the latent topic distribution over spatial items and that over content words associated with them, the intrinsic user interest distribution over topics, and the distribution of local preference in a given region over topics.

You can find all of my R codes and datasets in my Github repository here!

Feel free to email me or comment below if you have any questions.