Frequent Pattern Mining Based On Clustering and Association Rule Algorithm

Abstract

Decision making is considered as one of the most difficult tasks in restaurants as food items are perishable. Managers always want to analyze summaries of sales, to get aware of customer preferences, to figure out which items or combinations of items should be put on sale or to simply acquire various kinds of marketing information. To fulfill this need, this paper is aimed to provide customer's buying patterns of food items using data mining techniques. Analysis of sales data shows that some food items are sold frequently while some food products are sold rarely. This paper proposes a method that groups the food items as slow selling, medium-selling and fast selling items using KMedoids clustering algorithm. These clusters intern are given as input for the association rule mining based Apriori and Most Frequent Pattern Mining algorithm to generate frequent patterns. The proposed method helps restaurant manager in decision making.The frequent patterns generated may assist restaurant manager to formulate marketing strategies and maximize profit.The algorithm is evaluated by using standard data set and is compared with the results of other algorithms considering computational time and other parameters as quality measures.