Towards Addressing the Coverage Problem in Association Rule-Based Recommender Systems
Association rule mining is an actively studied topic in recommender systems. A major limitation of an association rule-based recommender system is the problem of reduced coverage. It is generally caused due to the usage of a single global minimum support (minsup) threshold in the mining process, which leads to the effect that no association rules involving rare items can be found. In the literature, Neighborhood-Restricted Rule-Based Recommender System (NRRS) using multiple minsups framework has been proposed to confront the problem. We have observed that NRRS is computationally expensive to use as it relies on an Apriori-like algorithm for generating frequent itemsets. Moreover, it has also been observed that NRRS can recommend uninteresting products to the users. This paper makes an effort to reduce the computational cost and improve the overall performance of NRRS. A pattern-growth algorithm, called MSFP-growth, has been proposed to reduce the computational cost of NRRS. We call the proposed framework as NRRS ⋆ . Experimental results show that NRRS ⋆ is efficient.
KeywordsRecommender system association rules and coverage problem
Unable to display preview. Download preview PDF.
- 1.Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. In: SIGMOD, pp. 207–216 (1993)Google Scholar
- 3.Smyth, B., McCarthy, K., Relly, J., O’Sullivan, D., McGinty, L., Wilson, D.C.: Case Studies in Association Rule Mining for Recommender System. In: IC-AI, pp. 809–815 (2005)Google Scholar
- 6.Liu, B., Hsu, W., Ma, Y.: Mining association rules with multiple minimum supports. In: KDD, pp. 337–341 (1999)Google Scholar
- 8.Uday Kiran, R., Krishna Reddy, P.: An Improved Multiple Minimum Support Based Approach to Mine Rare Association Rules. In: Proceedings of CIDM, pp. 340–347 (2009)Google Scholar
- 9.Uday Kiran, R., Krishna Reddy, P.: Novel techniques to reduce search space in multiple minimum supports-based frequent pattern mining algorithms. In: Proceedings of EDBT, pp. 11–20 (2011)Google Scholar
- 10.Uday Kiran, R., Krishna Reddy, P.: An Improved Neighborhood-Restricted Association Rule-based Recommender System Using Relative Support. To be Appeared in ADC (2013)Google Scholar