A single‐phase algorithm for mining high utility itemsets using compressed tree structures

Brahmavar, Anup; Harish, S; Geetha, M.

doi:10.4218/etrij.2020-0300

Cited by 5 publications

(3 citation statements)

References 24 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both the trees are constructed with a single database scan and are complete, that is, they do not discard any items. The details pertaining to the node structure and construction algorithms can be found in Reference 19. In its node, UCT stores the item along with the accumulated count and utility along the path in the tree.…”

Section: Pspuc: Parallel Single Phase Utility Computationmentioning

confidence: 99%

“…Thus, determining utility is rendered easier. The details pertaining to the pruning strategies and accessing SUT for utility computation can be found in Reference 19. Since SUT stores the utility information in a compact manner, an additional database scan can be completely avoided for utility computation.…”

Section: Pspuc: Parallel Single Phase Utility Computationmentioning

confidence: 99%

“…[15][16][17][18] Recently, a single-phase algorithm-SPUC (single-phase utility computation) using a compressed tree structure in conjunction with a prefix tree was proposed. 19 While the prefix tree called utility count tree (UCT) guided the mining process, the transaction compressed string utility tree (SUT) facilitated the utility computation without an additional database scan.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mining high utility itemsets with time‐aware scheduling using Apache Spark

Brahmavar

Venkatarama

Maiya

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Since the last decade, Market Basket Analysis has been propelled by augmentation of revenue information. Termed as high utility itemset mining (HUIM), this task considers the factors of purchase quantity and unit profit of the items in the transaction database. Although several sequential algorithms to mine HUIs exist, their performance degrades as the database becomes voluminous. Distributed computing solutions such as Apache Hadoop and Apache Spark have proven effective in alleviating this bottleneck. In this regard, the current study develops a parallel workflow to adapt a single‐phase tree‐based algorithm called the single phase utility computation (SPUC) algorithm on a Spark cluster. Based on the time taken to mine individual conditional pattern bases in SPUC, an assignment strategy that partitions the search space across the cluster is proposed in parallel SPUC (PSPUC) algorithm. Experimental evaluation conducted using real and synthetic datasets demonstrate that PSPUC outperforms PHUI‐Growth algorithm. Apart from this, PSPUC in conjunction with the time‐aware assignment strategy converges mining faster than a random assignment of items. A linear speedup of PSPUC is also demonstrated.

show abstract

Section: Pspuc: Parallel Single Phase Utility Computationmentioning

confidence: 99%

Section: Pspuc: Parallel Single Phase Utility Computationmentioning

confidence: 99%