@inproceedings{9e61cec86cae476e8acfa591a5b11f9c,
title = "EFIM: A highly efficient algorithm for high-utility itemset mining",
abstract = "High-utility itemset mining (HUIM) is an important data mining task with wide applications. In this paper, we propose a novel algorithm named EFIM (EFficient high-utility Itemset Mining), which introduces several new ideas to more efficiently discovers high-utility itemsets both in terms of execution time and memory. EFIM relies on two upper-bounds named sub-tree utility and local utility to more effectively prune the search space. It also introduces a novel array-based utility counting technique named Fast Utility Counting to calculate these upper-bounds in linear time and space. Moreover, to reduce the cost of database scans, EFIM proposes efficient database projection and transaction merging techniques. An extensive experimental study on various datasets shows that EFIM is in general two to three orders of magnitude faster and consumes up to eight times less memory than the state-of-art algorithms d2HUP, HUI-Miner, HUP-Miner, FHM and UP-Growth+.",
keywords = "High-utility mining, Itemset mining, Pattern mining",
author = "Souleymane Zida and Philippe Fournier-Viger and Lin, {Jerry Chun Wei} and Wu, {Cheng Wei} and Tseng, {Vincent Shin-Mu}",
year = "2015",
month = jan,
day = "1",
doi = "10.1007/978-3-319-27060-9_44",
language = "English",
isbn = "9783319270593",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "530--546",
editor = "Grigori Sidorov and Galicia-Haro, {Sof{\'I}a N.}",
booktitle = "Advances in Artificial Intelligence and Soft Computing - 14th Mexican International Conference on Artificial Intelligence, MICAI 2015, Proceedings",
address = "Germany",
note = "null ; Conference date: 25-10-2015 Through 31-10-2015",
}