Parametric Algorithms for Mining Share Frequent Itemsets

Barber, Brock; Hamilton, Howard J.

doi:10.1007/3-540-39963-1_59

Cited by 5 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, predictive approaches generally cannot ensure that the mining result contains the complete set of high utility itemsets [5,6,34,35]. To address this urgent problem, Li et al proposed the FSM algorithm, a non-exhaustive search method, to discover all SH-frequent itemsets [22].…”

Section: Existing Algorithmsmentioning

confidence: 99%

“…Carter et al [10] propose the share-confidence model to discover useful knowledge about numerical attributes associated with items in a transaction. Several other methods have since been proposed to efficiently discover share-frequent (SH-frequent) itemsets with infrequent subsets [4][5][6]17,18,[22][23][24]. Yao et al [34,35] generalize the share-confidence model [6] to develop the conventional utility mining model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Isolated items discarding strategy for discovering high utility itemsets

Yeh

Chang

2008

Data & Knowledge Engineering

248

139

View full text Add to dashboard Cite

Traditional methods of association rule mining consider the appearance of an item in a transaction, whether or not it is purchased, as a binary variable. However, customers may purchase more than one of the same item, and the unit cost may vary among items. Utility mining, a generalized form of the share mining model, attempts to overcome this problem. Since the Apriori pruning strategy cannot identify high utility itemsets, developing an efficient algorithm is crucial for utility mining. This study proposes the Isolated Items Discarding Strategy (IIDS), which can be applied to any existing level-wise utility mining method to reduce candidates and to improve performance. The most efficient known models for share mining are ShFSM and DCG, which also work adequately for utility mining as well. By applying IIDS to ShFSM and DCG, the two methods FUM and DCG+ were implemented, respectively. For both synthetic and real datasets, experimental results reveal that the performance of FUM and DCG+ is more efficient than that of ShFSM and DCG, respectively. Therefore, IIDS is an effective strategy for utility mining.

show abstract

Section: Existing Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Isolated items discarding strategy for discovering high utility itemsets

Yeh

Chang

2008

Data & Knowledge Engineering

248

139

View full text Add to dashboard Cite

show abstract

“…Moreover, they cannot rely on the downward closure property and therefore their searching methods are very time-consuming and do not work efficiently in large databases. Some other algorithms such as SIP, CAC and IAB [3], [4], [5] have been proposed to mine share-frequent patterns but they may not discover all the share-frequent patterns. The Fast Share Measure (ShFSM) [10] algorithm improves the previous algorithms by using the level closure property.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, traditional frequency/support measure cannot analyze the exact number of items (itemsets) purchased. Accordingly, itemset share approaches [3], [4], [5], [6], [10], [11] have been proposed to discover more important knowledge from databases. The share measure can provide useful knowledge about the numerical values that are typically associated with the transaction items.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Method for Incremental Mining of Share-Frequent Patterns

Ahmed

Tanbeer

Jeong

2010

2010 12th International Asia-Pacific Web Conference

View full text Add to dashboard Cite

The share measure of itemsets has been proposed to discover useful knowledge about numerical values associated with items in a transaction database. Therefore, share-frequent pattern mining problem becomes a very important research issue in data mining. However, the existing algorithms of share-frequent pattern mining are based on static databases. Moreover, they are not suitable for interactive mining. In this paper, we propose a novel tree structure IncrShrFP-Tree (Incremental Share-Frequent Pattern Tree) for incremental and interactive share-frequent pattern mining. It is effective for incremental and interactive mining to utilize the previous tree structure and to use the previous mining results when a database is updated or a minimum support threshold is changed. It needs maximum two database scans to calculate the resultant share-frequent patterns in incremental databases. Extensive performance analyses show that our method is very efficient for incremental and interactive share-frequent pattern mining.

show abstract

An efficient algorithm for mining complete share-frequent itemsets using BitTable and heuristics

Nawapornanan

Boonjing

2012

2012 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

This paper proposes a new efficient algorithm for mining share-frequent itemsets from BitT able knowledge -extracted once from a transaction database. The knowledge contains sufficient information for such a mining task and provides efficient interactive access. The algorithm finds all share-frequent itemsets by level-wise generating complete promising candidates from a BitT able using heuristics and testing for desired solutions. Simulation results reveal that the proposed algorithm perform significantly better than ShFSM and DeG both runtime and a number of generated candidates.

show abstract

Parametric Algorithms for Mining Share Frequent Itemsets

Cited by 5 publications

References 9 publications

Isolated items discarding strategy for discovering high utility itemsets

Isolated items discarding strategy for discovering high utility itemsets

An Efficient Method for Incremental Mining of Share-Frequent Patterns

An efficient algorithm for mining complete share-frequent itemsets using BitTable and heuristics

Contact Info

Product

Resources

About