A Context-Aware Recommender System Based On Collaborative Filtering In Restaurant Industry

Culture of going out for food is increasing, especially in metropolitan cities and finding a nearby restaurant that matches users’ interests and preferences is difficult therefore, designing and developing a restaurant recommender system can be an appropriate solution for this problem. Recommendation systems filter and recommend only relevant data to the user using different filtering techniques. This article focuses on presenting restaurant recommender systems by combining collaborative filtering and context aware filtering on dataset of restaurants in Tehran. We use location context and interest drift to improve our system accuracy. The results of the evaluations show that our model in comparison with the two recommended model of Tag-weight and USTTR has an improvement of 2.25% and 3.1% respectively, in terms of precision.

Keywords:

Context aware recommender system , restaurant industry , interest drift , collaborative filtering.