Fast and Memory Efficient Mining of High Utility Itemsets in Data Streams

Li, Hua-Fu; Huang, Hsin-Yun; Chen, Yi-Cheng; Liu, Yu-Jiun; Lee, Suh-Yin

doi:10.1109/icdm.2008.107

Cited by 66 publications

(44 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average size of the longest frequent itemset of both T10I6100K and T20I6D100K is six. Chess [12] is a dense dataset, with the number of transactions at 3,196, distinct items at 75, and average transaction length at 37. Each transaction contained nearly more than 49% items.…”

Section: Testing Datamentioning

confidence: 99%

“…The traditional frequent itemset mining algorithms often adopt one-fold item interest definition, which indicates that item utility is only related to statistical information, with 1 denoting the presence and 0 standing for the absence of such information. This single definition is inappropriate for real business applications [2][3]. For instance, the most common problem for managers is to identify or differentiate valuable customers from regular ones.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Approach for High Temporal Utility Item Mining

Pan¹,

Liu²,

Zhang³

2016

IJDTA

View full text Add to dashboard Cite

show abstract

Section: Testing Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast Approach for High Temporal Utility Item Mining

Pan¹,

Liu²,

Zhang³

2016

IJDTA

View full text Add to dashboard Cite

show abstract

“…This algorithm guarantees that the complete set of high utility itemsets will be identified correctly. [10,11,12] Then start level by transaction-weighted upward Closure Property. Generate one frequent item set and find one high utility item set, then two, three and so on For two candidate item set we use joining for each item with every other item From the table5,6,7 it is clear that high utility item set are…”

Section: Two Phase Methodsmentioning

confidence: 99%

Mining High Utility Itemsets from Large Dynamic Dataset by Eliminating Unusual Items

Chaudhari¹,

Verma²

2013

IJCA

View full text Add to dashboard Cite

Utility-based data mining is a new research area interested in all types of utility factors in data mining processes [1]. The basic meaning of utility is the quantity sold, interest, importance & profitability of items to the users. Utility of items in a transaction database consists of two aspects:1. The importance of distinct or unique items, which is called external utility. 2.The importance of the items in the transaction, w is called as internal utility.Mining high utility itemsets from the databases is not an easy task. Pruning search space for high utility itemset mining is difficult because a superset of a low utility itemset may be a high utility itemset. Existing studies [2,4,9] applied overestimated methods to facilitate the mining performance of utility mining. In these methods, first we will get potential high utility itemsets, and then an additional database scan is performed for identifying their utilities. However, the existing methods often generate a huge candidate itemsets and the mining performance is degraded consequently. In this paper we proposed Eliminating Unusual Itemset by Eliminating item set which is low utility item set to reduce search space. Proposed methods not only reduce the number of candidate itemsets, but also significantly increase the performance of the mining process.

show abstract

“…In this paper [20], two efficient sliding windowbased algorithms, MHUI-BIT (Mining High-Utility Itemsets based on BITvector) and MHUI-TID (Mining High-Utility Itemsets based on TIDlist), are proposed for mining highutility itemsets from data streams. The advantage is mining high-utility itemsets with negative item profits over stream transaction-sensitive sliding windows but memory issue cannot be overcome as expected.…”

Section: ) Manually Inspecting the Solution 4) Combinations Of The Amentioning

confidence: 99%

Extraction of High Utility Itemsets using Utility Pattern with Genetic Algorithm from OLTP System

Saranya¹

2015

IJRITCC

View full text Add to dashboard Cite

Abstract:To analyse vast amount of data, Frequent pattern mining play an important role in data mining. In practice, Frequent pattern mining cannot meet the challenges of real world problems due to items differ in various measures. Hence an emerging technique called Utility-based data mining is used in data mining processes.The utility mining not only considers the frequency but also see the utility associated with the itemsets.The main objective of utility mining is to extract the itemsets with high utilities, by considering user preferences such as profit,quantity and cost from OLTP systems. In our proposed approach, we are using UP growth with Genetic Algorithm. The idea is that UP growth algorithm would generate Potentially High Utility Itemsets and Genetic Algorithm would optimize and provide the High Utility Item set from it. On comparing with existing algorithm, the proposed approach is performing better in terms of memory utilization.

show abstract

Fast and Memory Efficient Mining of High Utility Itemsets in Data Streams

Cited by 66 publications

References 10 publications

Fast Approach for High Temporal Utility Item Mining

Fast Approach for High Temporal Utility Item Mining

Mining High Utility Itemsets from Large Dynamic Dataset by Eliminating Unusual Items

Extraction of High Utility Itemsets using Utility Pattern with Genetic Algorithm from OLTP System

Contact Info

Product

Resources

About