Association rule mining using treap

The analytical process designed to mine data became more difficult with the rapid information explosion. This in-turn created completely distributed and un-indexed data. Thus assessing and finding relations between variables from large database became a tedious task. There are various association rule mining algorithms available for this process, but a powerful association algorithm which runs in reduced time and space complexity is hard to find. In this work, we propose a new rule mining algorithm which works in a priority model for finding interesting relations in a database using the data structure Treap. While comparing with Apriori's O (e(n)) and FP growth's O (n(2)), the proposed algorithm finishes mining in O (n) in its best case analysis and in O (n log n) in its worst case analysis. This was found to be much better when compared to other algorithms of its kind. The results were evaluated and compared with the existing algorithm.