Flexible Frameworks for Actionable Knowledge Discovery

Longbing Cao, Yanchang Zhao, Huaifeng Zhang, Dan Luo, Chengqi Zhang, E. K. Park

IEEE Transactions on Knowledge and Data Engineering · 2009 · 80 citations · 28 references

Concepts

TL;DR

Data mining often stops at pattern discovery, yet many mined patterns are ignored by business users who lack actionable guidance, limiting the adoption of advanced techniques for improving enterprise operations. This work introduces a formal perspective on actionable knowledge discovery (AKD) that bridges system design and decision‑making. AKD is framed as a closed optimization pipeline that defines problems, designs models, and discovers actionable patterns, and the authors present four generic AKD frameworks—post‑analysis, unified‑interest, combined‑mining, and multisource combined‑mining—illustrated by a case study extracting debt‑prevention patterns from social‑security data. Experiments demonstrate that the proposed frameworks are general, flexible, and practical, effectively extracting actionable deliverables for immediate decision making across diverse complex problems.

Abstract

Most data mining algorithms and tools stop at the mining and delivery of patterns satisfying expected technical interestingness. There are often many patterns mined but business people either are not interested in them or do not know what follow-up actions to take to support their business decisions. This issue has seriously affected the widespread employment of advanced data mining techniques in greatly promoting enterprise operational quality and productivity. In this paper, we present a formal view of actionable knowledge discovery (AKD) from the system and decision-making perspectives. AKD is a closed optimization problem-solving process from problem definition, framework/model design to actionable pattern discovery, and is designed to deliver operable business rules that can be seamlessly associated or integrated with business processes and systems. To support such processes, we correspondingly propose, formalize, and illustrate four types of generic AKD frameworks: Postanalysis-based AKD, Unified-Interestingness-based AKD, Combined-Mining-based AKD, and Multisource Combined-Mining-based AKD (MSCM-AKD). A real-life case study of MSCM-based AKD is demonstrated to extract debt prevention patterns from social security data. Substantial experiments show that the proposed frameworks are sufficiently general, flexible, and practical to tackle many complex problems and applications by extracting actionable deliverables for instant decision making.

References

28