Evaluating the performance of apriori and predictive apriori algorithm to find new association rules based on the statistical measures of datasets
Mukesh Sharma, Jyoti Sharma Choudhary, Gunjan Sharma · 2012
various advancements has emerged in the field of data mining. One of the hottest topic in this area is mining for association rules from the existing massive collection of datasets. The pattern obtained from these databases are used in various fields like super market sales-prediction, fraud detection and weather forecasting etc. So it is necessary that only strong rules are mined by using appropriate algorithm. In this paper, out of the various existing algorithms of association rule mining, two most important algorithm i.e. apriori and predictive apriori algorithm are chosen for experiment. Their performance is compared based on the interesting measures using weka3.7.5 which is a java based machine learning tool. After that ,various statistical measures are calculated of different datasets and then based on the comparison of algorithms and statistical measures of data, new rules are generated using see5 tool.