In the last decade, data mining has emerged as one of most vivacious areas in information technology. Although many algorithms and techniques for data mining have been proposed, it still remains an open problem to successfully apply them to discover and deliver actionable knowledge in real-life applications in various domains.


Motivation of DDDM

Real-world data mining generally must consider domain experts’ roles, and it must involve specific domain knowledge, more general human intelligence, network intelligence, social intelligence, and domain-specific constraints. Organizational factors and social issues are also important in practice. However, it is very challenging to involve domain factors in mining real-world enterprise applications. Even more challenging is the issue of discovering knowledge that can support business people who are taking domain-pertinent decision-making actions. In fact, it has been argued that actionable knowledge discovery in real-life enterprise applications is one of the grand challenges of the next-generation Data Mining. Domain-driven data mining (D3M) seeks principles, methodologies, frameworks, techniques and tools for tackling the above challenges. It will develop next-generation Data Mining methodologies and techniques for actionable knowledge discovery that synthesize the ubiquitous intelligence surrounding the comprehensive problem domains.

Domain Driven Data Mining (D3M) aims at original, cutting-edge and state-of-the-art theoretical and applied contributions that make efforts

1. to expose next-generation data mining methodologies, frameworks and processes towards actionable knowledge discovery and delivery,
2. to investigate effective (automated, human-centred and/or human-machine-cooperated) principles and techniques for acquiring, representing, modeling and engaging ubiquitous intelligence in real-world data mining,
3. to develop workable and operable tools and systems balancing technical significance and business concerns, and delivering actionable knowledge expressed as operable business rules seamlessly engaging business processes and systems, and
4. to discuss trends and directions of next-generation Data Mining theories and applications.

Tasks of DDDM

DDDM targets the relevant areas including (but not limited to) the following:

•  Challenges and future directions for next-generation data mining
•  Next-generation data mining methodology and project management
•  Next-generation data mining framework, system support and infrastructure
•  Involvement and integration of ubiquitous intelligence, including human intelligence, domain intelligence, network intelligence, organizational intelligence and social intelligence in data mining
•  Formalization of ubiquitous intelligence in data mining
•  Engaging and modeling dynamic supervision, adaptation, expert group, situated cognition and group decision in data mining
•  Organizational, environmental and social factors in data mining
•  Intelligence meta-synthesis in data mining
•  Next-generation data mining evaluation system
•  Presentation and delivery of data mining deliverables
•  Domain-specific case studies and enterprise applications

 
Activities and resources related to DDDM

Workshops:

• Domain-driven data mining 2008, joint with ICDM2008
  (http://datamining.it.uts.edu.au/dddm08/)
• Domain-driven data mining 2007, joint with SIGKDD2007
  (http://datamining.it.uts.edu.au/dddm/)

Special issues:

• Domain-driven data mining, IEEE Trans. Knowledge and Data Engineering, 2009.
• Domain-driven, actionable knowledge discovery, IEEE Intelligent Systems, Department, 22(4): 78-89, 2007.

Tutorial:

• Domain-Driven Data Mining: Empowering Actionable Knowledge Delivery, PAKDD2009 Tutorial., joint with PAKDD2009