Market Basket Analysis for Determine Goods Layout Using FP-Growth Algorithm

Abstract

The retail industry has undergone a significant transformation. Jumbo Mart is one of the retail businesses that consistently meet customer needs in Pekanbaru city. The number of similar businesses makes Jumbo Mart need to have a competitive advantage to compete. One of them is by improving the shopping experience, especially in the aspect of goods layout. However, based on observations and interviews, the determination of the layout of goods at Jumbo Mart is still not optimal. The number of products and variety of items sold is one of the reasons. In addition, customer transaction history has not been used further and is only stored as an archive of monthly reports. Whereas analyzing the data can be an effective solution in arranging the layout of goods based on customer behavior. Therefore, this research proposes a data mining technique with the FP-Growth algorithm to find association rules between categories of goods. The implementation results with a minimum support value of 15% and confidence of 50% get 7 association rules, but only 6 are proven valid. The valid association rules are then proposed to be placed close together so that it can make it easier for buyers to find the desired items. In addition, items with the consumption category are dominant as consequents, which can be found in the four association rules. This indicates that items with consumption categories have great appeal and are an important part of customers' shopping behavior and habits.