The development of technology in the field of business grows rapidly day by day. The use of technology in business can help company deploying best business strategies to compete with others. Companies can take advantage of sales data to discover more information that can help them make decisions. Using data mining approach, companies can process transaction data in order to find out consumer buying patterns. In this paper, the authors implement the association rules mining or often referred to as Market Basket Analysis for transaction data processing using RapidMiner by comparing FP-Growth and Apriori algorithm. The results of this study from 1641 transaction rows data, with minimum support of 0.09 and confidence of 0.9, is that the Fp-Growth needs 6 seconds to produce 19 rules and forms a combination of 3 itemset with a rule strength of 112.66%. and an accuracy of 217%. While the Apriori 30 second algorithm produces 6 rules and forms a combination of 3 items with a rule strength of 52.47% and an accuracy of 46%. From the results of the comparison of algorithms, it can be concluded that the Fp-Growth algorithm is better than the Apriori algorithm.