Extraction Rules from Educational Data using FP Growth Algorithm with Correlation

Abstract

Educational data mining is discovering knowledge from data that come from educational environment. This paper presents finding interesting patterns from educational database. Learning how student behaviors relate to academic results, could improve the teaching system. Association rule mining is used to find the interesting patterns, from which student behaviors can be learned. Correlation value, measured by lift ratio is used to measure the interestingness. The statistical index of the degree to which two variables are associated is the correlation coefficient. The lift value of greater than 1 indicates a positive correlation between antecedent and consequent. FP Growth algorithm is used to implement the association rule.