Development of recommendation systems using game theoretic techniques

In the present work, we inquire use of game theoretic techniques for development recommender systems. Initially, interaction two aspects systems, query reformulation and relevance estimation, is modelled as a cooperative where players have common utility, to supply optimal recommendations, which they try maximize. Based on this modelling, three basic recommendation methods are developed, namely collaborative filtering, content based filtering demographic filtering. The different then combined create hybrid weighted combination, extended, it game. Finally, with genetic algorithm theory used parent selection process. Our work offers baseline efficient combination through in addition novelty method, Choice by Game, process algorithms consistent performance improvements.