Flexible Frameworks for Actionable Knowledge Discovery

被引：52

作者：

Cao, Longbing ^{[1
]}

Zhao, Yanchang ^{[1
]}

Zhang, Huaifeng ^{[1
]}

Luo, Dan ^{[1
]}

Zhang, Chengqi ^{[1
]}

Park, E. K. ^{[2
]}

机构：

[1] Univ Technol Sydney, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia

[2] CUNY Coll Staten Isl, Staten Isl, NY 10314 USA

来源：

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING | 2010年 / 22卷 / 09期

基金：

澳大利亚研究理事会;

关键词：

Data mining; domain-driven data mining (D-3 M); actionable knowledge discovery; decision making; DOMAIN-DRIVEN;

D O I：

10.1109/TKDE.2009.143

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：1299 / 1312

页数：14

共 42 条

[21]

Freitas AA, 1998, LECT NOTES ARTIF INT, V1510, P1

[22]

Hilderman RJ, 2000, LECT NOTES COMPUT<D>, V1910, P432

[23]

KARGUPTA H, 1999, ADV DISTRIBUTED DATA

[24] A microeconomic view of data mining [J].

Kleinberg, J ;

Papadimitriou, C ;

Raghavan, P .

DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (04) :311-324

[25] Clustering association rules [J].

Lent, B ;

Swami, A ;

Widom, J .

13TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING - PROCEEDINGS, 1997, :220-231

[26] Analyzing the subjective interestingness of association rules [J].

Liu, B ;

Hsu, W ;

Chen, S ;

Ma, YM .

IEEE INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 2000, 15 (05) :47-55

[27]

LIU B, 1996, P NAT C ART INT INN

[28]

LIU B, 1999, P ACM SIGKDD

[29] Alternative interest measures for mining associations in databases [J].

Omiecinski, ER .

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2003, 15 (01) :57-69

[30]

Padmanabhan B., 1998, Proceedings Fourth International Conference on Knowledge Discovery and Data Mining, P94

← 1 2 3 4 5 →