<![CDATA[A method known as data mining is used to discover hidden patterns in very large data sets. Shopping cart analysis, also known as "shopping cart analysis," is one of the most common techniques in the retail industry that utilizes association rules. The focus of this study is to discover association patterns between the Apriori Algorithm and FP-Growth on sales transaction data of information technology (IT) products in a retail store. The dataset used consists of 7,496 transactions, with a maximum of 20 items and an average of 3.91 items, respectively. The raw data before analysis contained 137 different product names. After preprocessing and name standardization, 75 products met the minimum support threshold of 1%. They were also tested with a minimum support parameter of 1% and a minimum confidence level of 30%. Both algorithms generated 253 frequently occurring itemsets and 63 association rules. The SanDisk Ultra 64GB and SanDisk Ultra 128GB microSDXC cards had the highest lift score of 3.4225. By requiring only two database scans, FP-Growth excels in computational efficiency. One can use these results to create cross-selling and reordering strategies.]]>
Copyrights © 2026
