Determination of the best rule-based analysis results from the comparison of the Fp-Growth, Apriori, and TPQ-Apriori Algorithms for recommendation systems

The popular association rule algorithms are Apriori and fp-growth; both of these very familiar among data mining researchers; however, there some weaknesses found in the algorithm, including long dataset scans process finding frequency item set, using large memory, resulting rules being sometimes less than optimal. In this study, authors made a comparison fp-growth, Apriori, TPQ-Apriori to analyze results three algorithms. TPQ- is an algorithm developed from algorithm. For experiments, fp-growth use RapidMiner Weka tools, while TPQ-apriori uses self-built application programs. used sales for Kopegtel NTB department store, which has been uploaded on Kaggle site. As testing base overall with good 100%, 50%, 25% total volume dataset, conclusion can be drawn that larger processed, will more optimal when RapidMiner, but not if processed small. It different FP-growth algorithms, where Several do appear because two have tolerance value Weka's tools support displayed. Meanwhile, capable producing datasets small datasets.