Context-based awareness in location recommendation system to enhance recommendation quality: A review

Abstract

Location recommendation system always involves huge volumes of data, therefore causes the scalability issues which not only increased processing time but cause reduced accuracy as well. Various techniques of recommendation system were developed to overcome this problem. Collaborative filtering is a technique that has a high accuracy in the location recommendation system, but has a weakness in terms of scalability. In addition, context-awareness approach is being developed by utilizing user contextual information, to produce more precise recommendation according to user's preferences. Some studies have shown that to achieve qualified recommendation for the user, their systems used context-awareness approach. The aim of this study is to review the technique of location recommendation system that uses the context-awareness to improve their performance in term of accuracy and scalability. The result of study shows that the implementation of context-awareness on a recommendation system gave the best result for recommending personalized location rather than a recommendation system without context-awareness. A study that uses context-awareness in the location recommendation system can achieve up to 58% precision and provide better recommendations for user. By developing DBSCAN, Singular Value Decomposition (SVD) or deep learning algorithm can produce lower scalability with high accuracy in location recommendation system.