A Novel Personalized Recommendation Model based on Location Computing

We propose a novel personalized recommendation model for social network users based on location computing. The novelty of our model is that we deal with the location based recommendation by combing logistic regression with collaborative filtering method. The logistic regression is used to train the weights of items' features, i.e., the recommendation sort list. On the other hand, the collaborative filtering is adopted to adjust the sort list by utilizing users' history. The proposed model takes into consideration the location, which defines the geographical boundaries of recommended items. The model's results represent both the popularity of all social users, but also the individual interest. Thus it serves as a personalized recommendation model. Experimental results on real-life data show that our model exhibits higher accuracy than other relevant recommendation system.