Knowledge actionability: satisfying technical and business interestingness
International Journal of Business Intelligence and Data MiningPublished 1 January 2007
Longbing Cao, Dan Luo, Chengqi Zhang
Citations48
SJR quartileQ4
SJR score0.15
SNIP0.24
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A two-way significance framework for measuring knowledge actionability is proposed, which highlights both technical interestingness and domain-specific expectations, and a fuzzy interestingness aggregation mechanism is developed to generate a ranked final pattern set balancing technical and business interests.
Abstract
Traditionally, knowledge actionability has been investigated mainly by developing and improving technical interestingness. Recently, initial work on technical subjective interestingness and business-oriented profit mining presents general potential, while it is a long-term mission to bridge the gap between technical significance and business expectation. In this paper, we propose a two-way significance framework for measuring knowledge actionability, which highlights both technical interestingness and domain-specific expectations. We further develop a fuzzy interestingness aggregation mechanism to generate a ranked final pattern set balancing technical and business interests. Real-life data mining applications show the proposed knowledge actionability framework can complement technical interestingness while satisfy real user needs.
Keywords
Computer ScienceBusiness, Management and Accounting
Market microstructure theory
1,351 Citations1995Maureen O’Hara
MetaCost
1,294 Citations1999Pedro Domingos
A principled method for making an arbitrary classifier cost-sensitive by wrapping a cost-minimizing procedure around it is proposed, called MetaCost, which treats the underlying classifier as a black box, requiring no knowledge of its functioning or change to it.
The Journal of FinanceData‐Snooping, Technical Trading Rule Performance, and the Bootstrap
1,048 Citations1999Ryan J. Sullivan, Allan Timmermann +1 more
IEEE Transactions on Knowledge and Data EngineeringWhat makes patterns interesting in knowledge discovery systems
675 Citations1996Abraham Silberschatz, Alexander Tuzhilin
The focus of the paper is on studying subjective measures of interestingness, which are classified into actionable and unexpected, and the relationship between them is examined.
On subjective measures of interestingness in knowledge discovery
357 Citations1995Avi Silberschatz, Alexander Tuzhilin
The purpose of this paper is to lay the groundwork for a comprehensive study of subjective measures of interestingness and classify these measures into actionable and unexpected, and examine the relationship between them.
A belief-driven method for discovering unexpected patterns
243 Citations1998Balaji Padmanabhan
This paper proposes a new method of discovering unexpected patterns that takes into consideration prior background knowledge of decision makers and uses these beliefs to seed the search for patterns in data that contradict the beliefs.
IEEE Intelligent Systems and their ApplicationsAnalyzing the subjective interestingness of association rules
232 Citations2000Bing Liu, Wynne Hsu +2 more
This article describes how the interestingness analysis system (IAS) leverages the user's existing domain knowledge to analyze discovered associations and then rank discovered rules according to various interestingness criteria, such as conformity and various types of unexpectedness.
Data Mining and Knowledge DiscoveryA Microeconomic View of Data Mining
194 Citations1998Jon Kleinberg, Christos H. Papadimitriou +1 more
A rigorous framework, based on optimization, for evaluating data mining operations such as associations and clustering, in terms of their utility in decision-making is presented.
ACM SIGKDD Explorations NewsletterA critical review of multi-objective optimization in data mining
193 Citations2004Alex A. Freitas
The general conclusions are that the weighted formula approach is to a large extent an ad-hoc approach for multi-objective optimization, whereas the lexicographic and the Pareto approach are more principled approaches, and therefore deserve more attention from the data mining community.
Lecture notes in computer scienceOn objective measures of rule surprisingness
137 Citations1998Alex A. Freitas
This paper has a twofold goal: showing that it is indeed possible to define objective (rather than subjective) measures of discovered rule surprisingness, and proposing new ideas and methods for defining objectiveRule surprisingness measures.
Lecture notes in computer scienceProfit Mining: From Patterns to Actions
88 Citations2002Ke Wang, Senqiang Zhou +1 more
This work builds a model for recommending target items and promotion strategies to new customers, with the goal of maximizing the net profit, and evaluates the effectiveness of this approach using data sets of a wide range of characteristics.
IEEE Intelligent SystemsDomain-Driven, Actionable Knowledge Discovery
83 Citations2007Longbing Cao, Chengqi Zhang +11 more
Data mining increasingly faces complex challenges in the real-life world of business problems and needs and both researchers and practitioners are realizing the importance of domain knowledge to close this gap and develop actionable knowledge for real user needs.
Postprocessing decision trees to extract actionable knowledge
78 Citations2004Qiang Yang, Jie Yin +2 more
A novel algorithm is presented that suggest actions to change customers from an undesired status to a desired one while maximizing objective function: the expected net profit.
International Journal of Pattern Recognition and Artificial IntelligenceTHE EVOLUTION OF KDD: TOWARDS DOMAIN-DRIVEN DATA MINING
70 Citations2007Longbing Cao, Chengqi Zhang
IEEE Transactions on Knowledge and Data EngineeringMining Impact-Targeted Activity Patterns in Imbalanced Data
62 Citations2008Longbing Cao, Yanchang Zhao +1 more
Algorithms are developed to mine frequent positive-impact and negative-impact oriented activity patterns, sequential impact-contrasted activity patterns (P is frequently associated with both pattern P rARR T and P rarr Tmacr macr in separated data sets), and sequential impact
Item selection by "hub-authority" profit ranking
61 Citations2002Ke Wang, Ming-Yen Thomas Su
This paper draws an analogy between the influence of cross-selling effect and the mutual reinforcement of hub/authority web pages to present a novel approach to the item ranking problem and applies this ranking approach to solve two selection problems.
Mining Actionable Patterns by Role Models
51 Citations2006Ke Wang, Yuelong Jiang +1 more
This work introduces the notion of "action" as a domain-independent way to model the domain knowledge and presents several pruning strategies taking into account the actionability requirement to reduce the search space, and algorithms for mining all actionable patterns.
International Journal of Intelligent SystemsAction rules mining
50 Citations2005Angelina A. Tzacheva, Zbigniew W. Raś
A heuristic strategy for constructing feasible action rules that have high confidence and possibly the lowest cost is proposed, and a new subclass of attributes called semi‐stable attributes is introduced.
MPIS: maximal-profit item selection with cross-selling considerations
45 Citations2004Raymond Chi-Wing Wong, Ada Wai-Chee Fu +1 more
This work proposes a new approach to the problem with the consideration of the loss rule - a kind of association rule to model the cross-selling effect and shows that the problem can be transformed to a quadratic programming problem.
Lecture notes in computer scienceApplying Objective Interestingness Measures in Data Mining Systems
45 Citations2000Robert J. Hilderman, Howard J. Hamilton
A two-step process for ranking the interestingness of discovered patterns that utilizes the chi-square test for independence in the first step and objective measures of interestingness in the second step is described that can be applied to ranking characterized/generalized association rules and data cubes.
International Journal of Data Warehousing and MiningDomain-Driven Data Mining
41 Citations2006Longbing Cao, Chengqi Zhang
This article proposes a practical data mining methodology referred to as domain-driven data mining, which targets actionable knowledge discovery in a constrained environment for satisfying user preference and illustrates some examples in mining actionable correlations in Australian Stock Exchange.
ACM SIGKDD Explorations NewsletterTowards effective and interpretable data mining by visual interaction
40 Citations2002Charų C. Aggarwal
A number of recent approaches to several data mining algorithms along these lines are discussed, which combine the computational power of a computer and the intuitive abilities of a human to provide solutions which cannot be achieved by either.
International Journal of Intelligent SystemsUnified algorithm for undirected discovery of exception rules: Research Articles
26 Citations2005Einoshin Suzuki, Jan M. Żytkow
Decision Support SystemsBridging the gap between business objectives and parameters of data mining algorithms
22 Citations1997Özden Gür Ali, William A. Wallace
This paper proposes and applies an experimental approach using a classification algorithm, Probabilistic Inductive Learning, to develop a mapping between the performance measures and the parameters of the algorithm used to analyze the data.
Agent Services-Based Infrastructure for Online Assessment of Trading Strategies
20 Citations2004Cao, L, Wang, J +2 more
Maximum profit mining and its application in software development
20 Citations2006Charles X. Ling, Victor S. Sheng +2 more
An Escalation Prediction (EP) system that mines historic defect report data and predicts the escalation risk of the defects for maximum net profit to suggest that the cost-sensitive decision tree is the best method for producing the highest positive net profit and comprehensible results.
International Journal of Intelligent Systems Technologies and ApplicationsMining in-depth patterns in stock market
19 Citations2008Lin Li, Longbing Cao
A decision support in-depth trading pattern discovery system with Robust Genetic Algorithms (RGA) that integrates expert knowledge and considers domain constraints into the trading rule development and uses this technique to mine actionable stock-rule pairs targeting behaviour with high return at low risk.
Human Involvement and Interactivity of the Next Generation’s Data Mining Tools
17 Citations2001Mihael Ankerst
To achieve the goal that the user steers and monitors the information flow without burdening him performing tasks that can be done automatically, an interface for human involvement has to be well designed and integrated in the KDD process.
Lecture notes in computer scienceFuzzy Genetic Algorithms for Pairs Mining
13 Citations2006Longbing Cao, Dan Luo +1 more
Lecture notes in computer scienceIntelligence Metasynthesis in Building Business Intelligence Systems
4 Citations2007Longbing Cao, Chengqi Zhang +2 more
A new framework for constructing next-generation BI systems is proposed based on real-world experience and practice in designing and implementing BI systems and greatly benefits from multi-disciplinary knowledge dialog such as complex intelligent systems and cognitive sciences.
Oxford University Press eBooksKnowledge evaluation: Other evaluations: usefulness, novelty, and integration of interesting news measures
4 Citations2002Alexander Tuzhilin
This article focuses on subjective methods of evaluation of discovered patterns in data that depend not only on the structure of the pattern and the data but also on the user who examines the pattern.