An evolutionary clustering algorithm based on temporal features for dynamic recommender systems

The use of internet and Web services is changing the way we use resources and communicate since the last decade. Although, this usage has made life easier in many respects still the problem of finding relevant information persists. A naive user faces the problem of information overload and continuous flow of new information makes the problem more complex. Furthermore, user's interests also keeps on changing with time. Several techniques deal with this problem and data mining is widely used among them. Recommender Systems (RSs) assist users in finding relevant information on the web and are mostly based on data mining algorithms. This paper addresses the problem of user requirements changing over a period of time in seeking information on web and how RSs deal with them. We propose a Dynamic Recommender system (DRS) based on evolutionary clustering algorithm. This clustering algorithm makes clusters of similar users and evolves them depicting accurate and relevant user preferences over time. The proposed approach performs an optimization of conflicting parameters instead of using the traditional evolutionary algorithms like genetic algorithm. The algorithm has been empirically tested and compared with standard recommendation algorithms and it shows considerable improvement in terms of quality of recommendations and computation time. (C) 2013 Elsevier B.V. All rights reserved.