Recursive Association Rule Mining

Abdelkader Mokkadem (1) , Mariane Pelletier , Louis Raimbault

1 LMV - Laboratoire de Mathématiques de Versailles

Mining frequent itemsets and association rules is an essential task within data mining and data analysis. In this paper, we introduce PrefRec, a recursive algorithm for finding frequent itemsets and association rules. Its main advantage is its recursiveness with respect to the items. It is particularly efficient for updating the mining process when new items are added to the database or when some are excluded. We present in a complete way the logic of the algorithm as well as its various applications. Finally we present experiments carried out in the R language comparing PrefRec with Apriori and Eclat the two most powerful algorithms in this language. To achieve this we built an R package to run our algorithm.

Domaines: Statistiques [stat]

Abdelkader Mokkadem, Mariane Pelletier, Louis Raimbault. Recursive Association Rule Mining. 2020. ⟨hal-03029729⟩