Domain-Driven Data Mining: A Practical Methodology

Extant data mining is based on data-driven methodologies. It either views data mining as an autonomous data-driven, trial-and-error process or only analyzes business issues in an isolated, case-by-case manner. As a result, very often the knowledge discovered generally is not interesting to real business needs. Therefore, 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. The domain-driven data mining consists of a DDID-PD framework that considers key components such as constraint-based context, integrating domain knowledge, human-machine cooperation, in-depth mining, actionability enhancement, and iterative refinement process. We also illustrate some examples in mining actionable correlations in Australian Stock Exchange, which show that domain-driven data mining has potential to improve further the actionability of patterns for practical use by industry and business.

[1]  Carsten Pohle.  Integrating and Updating Domain Knowledge with Data Mining , 2003, VLDB PhD Workshop.

[2]  Longbing Cao,et al.  Agent services-based infrastructure for online assessment of trading strategies , 2004 .

[3]  H. White,et al.  Data‐Snooping, Technical Trading Rule Performance, and the Bootstrap , 1999 .

[4]  David Taniar,et al.  Parallel Data Mining , 2002 .

[5]  Chengqi Zhang,et al.  Domain-Driven Actionable Knowledge Discovery in the Real World , 2006, PAKDD.

[6]  Jaideep Srivastava,et al.  Selecting the right interestingness measure for association patterns , 2002, KDD.

[7]  Longbing Cao,et al.  Human-Computer-Cooperated Intelligent Information System Based on Multi-Agents , 2003 .

[8]  Gregory Piatetsky-Shapiro,et al.  Summary from the KDD-03 panel: data mining: the next 10 years , 2003, SKDD.

[9]  Xiaohui Liu,et al.  Data mining from 1994 to 2004: an application-orientated review , 2005, Int. J. Bus. Intell. Data Min..

[10]  Mihael Ankerst,et al.  Report on the SIGKDD-2002 panel the perfect data mining tool: interactive or automated? , 2002, SKDD.

[11]  Balaji Padmanabhan,et al.  A Belief-Driven Method for Discovering Unexpected Patterns , 1998, KDD.

[12]  Matthias Klusch,et al.  The role of agents in distributed data mining: issues and benefits , 2003, IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003..

[13]  Lawrence J. Henschen,et al.  Using domain knowledge in knowledge discovery , 1999, CIKM '99.

[14]  Edward Omiecinski,et al.  Alternative Interest Measures for Mining Associations in Databases , 2003, IEEE Trans. Knowl. Data Eng..

[15]  Mohammed J. Zaki,et al.  Systems support for scalable data mining , 2000, SKDD.

[16]  Boris Kovalerchuk,et al.  Data mining in finance: advances in relational and hybrid methods , 2000 .

[17]  Li Lin,et al.  Mining in-depth patterns in stock market , 2008, Int. J. Intell. Syst. Technol. Appl..

[18]  Longbing Cao,et al.  Agent-Oriented Metasynthetic Engineering for Decision Making , 2003, Int. J. Inf. Technol. Decis. Mak..

[19]  Pedro M. Domingos.  Prospects and challenges for multi-relational data mining , 2003, SKDD.

[20]  Zili Zhang,et al.  Agents and Data Mining: Mutual Enhancement by Integration , 2005, AIS-ADM.

[21]  Sikha Bagui,et al.  An Approach to Mining Crime Patterns , 2006, Int. J. Data Warehous. Min..

[22]  Ronen Feldman,et al.  The Data Mining and Knowledge Discovery Handbook , 2005 .

[23]  Chengqi Zhang,et al.  Ontology-based integration of business intelligence , 2006, Web Intell. Agent Syst..

[24]  William A. Wallace,et al.  Bridging the gap between business objectives and parameters of data mining algorithms , 1997, Decis. Support Syst..

[25]  Charu C. Aggarwal,et al.  Towards effective and interpretable data mining by visual interaction , 2002, SKDD.