IGCRGA: A Novel Heuristic Approach for Personalization of Cold Start Problem

IGCRGA, an acronym for Information Gain Clustering through Rank Based Genetic Algorithm, is a novel heuristic used in Recommender System (RS) for solving personalization problems. In a bid to improve th equality of recommendation of RS and to alleviate the problem associated with personalization heuristics, which use fitness value in the clustering process, IGCRGA is proposed in this work. Besides, IGCRGA using the technique of global minim a still resolves the problem associated with IGCN (Information Gain Clustering Neighbor) which traps the algorithm in local clustering centroids. Although this problem was alleviated by both IGCGA (Information Gain Clustering through Genetic Algorithm) and IGCEGA (Information Gain Clustering through Elitist Genetic Algorithm), IGCRGA solves the problem even better because IGCRGA assumes the lowest Mean Absolute Error (MAE), the evaluation matrix used in this work. Experimentation of the various heuristics /techniques in RS used in personalization for cold start problems was conducted and a comparison of the irrespective MAE was performed. The various heuristics /techniques explored include: Popularity, Entropy, IGCN, IGCGA, IGCEGA and IGCRGA. The result showed that IGCRGA is associated with the lowest MAE, therefore, best clustering, which in turn results into best recommendation.