Applying Objective Interestingness Measures in Data Mining Systems

Hilderman, Robert J.; Hamilton, Howard J.

doi:10.1007/3-540-45372-5_47

Cited by 39 publications

(32 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although there have been some reports of actionable knowledge discovery [8,9,10,16] and selecting actionable patterns/rules or interestingness measures in association rule mining [1,2,4,15,17], none of the previous research considers how to select actionable positive and negative sequential patterns. Very few papers study NSP mining [12,19,20,21,24,26,27], and most primarily focus on how to design a mining algorithm and how to improve the algorithm's efficiency.…”

Section: K/2] M=1mentioning

confidence: 99%

“…Therefore, this paper investigates association rule mining. In this area, some methods have been proposed to prune uninteresting itemsets, to select actionable patterns, to mine positive and negative association rules, and so on [2,4,15,17]. Among these methods, the one proposed by X.D.…”

Section: K/2] M=1mentioning

confidence: 99%

“…Some literature has proposed a few measures to mine interesting association rules, such as correlation coefficients, chi-squared tests, interestingness, Laplace, the Gini-index, Piatetsky-Shapiro method, conviction and so on [2,4,15,17]. M.L.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Select actionable positive or negative sequential patterns

Xiang

Liu

et al. 2015

IFS

View full text Add to dashboard Cite

Abstract. Negative sequential patterns (NSP) refer to sequences with non-occurring and occurring items, and can play an irreplaceable role in understanding and addressing many business applications. However, some problems occur after mining NSP, the most urgent one of which is how to select the actionable positive or negative sequential patterns. This is due to the following factors: 1) positive sequential patterns (PSP) mined before considering NSP may mislead decisions; and 2) it is much more difficult to select actionable patterns after mining NSP, as the number of NSPs is much greater than PSPs. In this paper, an improved method of pruning uninteresting itemsets to fit for a selecting actionable sequential pattern (ASP) is proposed. Then, a novel and efficient method, called SAP, is proposed to select the actionable positive and negative sequential patterns. Experimental results indicate that SAP is very efficient in the selection of ASP. To the best of our knowledge, SAP is the best method for the selection of actionable positive and negative sequential patterns.

show abstract

Section: K/2] M=1mentioning

confidence: 99%

Section: K/2] M=1mentioning

confidence: 99%

See 1 more Smart Citation

Select actionable positive or negative sequential patterns

Xiang

Liu

et al. 2015

IFS

View full text Add to dashboard Cite

show abstract

“…This approach applies to a variety of computing scenarios. For example, a related concept was studied in [15,21] for measuring the "interestingness" of textual data by comparing it to an expected model, usually with the Kullback-Liebler (KL) divergence.…”

Section: Phase 6: Privacy-preserving Aggregation and Pricingmentioning

confidence: 99%

What’s the Gist? Privacy-Preserving Aggregation of User Profiles

Bilogrevic

Freudiger²,

Cristofaro

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Over the past few years, online service providers have started gathering increasing amounts of personal information to build user profiles and monetize them with advertisers and data brokers. Users have little control of what information is processed and are often left with an all-or-nothing decision between receiving free services or refusing to be profiled. This paper explores an alternative approach where users only disclose an aggregate model -the "gist" -of their data. We aim to preserve data utility and simultaneously provide user privacy. We show that this approach can be efficiently supported by letting users contribute encrypted and differentially-private data to an aggregator. The aggregator combines encrypted contributions and can only extract an aggregate model of the underlying data. We evaluate our framework on a dataset of 100,000 U.S. users obtained from the U.S. Census Bureau and show that (i) it provides accurate aggregates with as little as 100 users, (ii) it generates revenue for both users and data brokers, and (iii) its overhead is appreciably low.

show abstract

“…Ranking similarities between measures was conducted by Hilderman, Hamilton and Barber (1999a) using the Gamma correlation coefficient. In this paper, the Spearman's rank correlation coefficient is used.…”

Section: Similarity Studymentioning

confidence: 99%

On Mining Summaries by Objective Measures of Interestingness

2006

View full text Add to dashboard Cite

Abstract. Knowledge discovery in databases is used to discover useful and understandable knowledge from large databases. A process of knowledge discovery consists of two steps, the data mining step and the evaluation step. In this paper, evaluating and ranking the interestingness of summaries generated from databases, which is a part of the second step, is studied using diversity measures. Sixteen previously analyzed diversity measures of interestingness are used along with three not previously considered ones, brought from different well-known areas. The latter three measures are evaluated theoretically according to five principles that a measure must satisfy to be qualified acceptable for ranking summaries. A theoretical correlation study between the eight measures that satisfy all five principles is presented based on mathematical proofs. An empirical evaluation is conducted using three real databases. Then, a classification of the eight measures is deduced. The resulting classification is used to reduce the number of measures to only two, which are the best over all criteria, and that produce non-similar results. This helps the user interpret the most important discovered knowledge in his decision making process.

show abstract

Applying Objective Interestingness Measures in Data Mining Systems

Cited by 39 publications

References 10 publications

Select actionable positive or negative sequential patterns

Select actionable positive or negative sequential patterns

What’s the Gist? Privacy-Preserving Aggregation of User Profiles

On Mining Summaries by Objective Measures of Interestingness

Contact Info

Product

Resources

About