TOP-10 DATA MINING CASE STUDIES

被引:4
|
作者
Melli, Gabor [1 ]
Wu, Xindong [2 ]
Beinat, Paul [3 ]
Bonchi, Francesco [4 ]
Cao, Longbing [5 ]
Duan, Rong [6 ]
Faloutsos, Christos [7 ]
Ghani, Rayid [8 ]
Kitts, Brendan [9 ]
Goethals, Bart [10 ]
Mclachlan, Geoff [11 ]
Pei, Jian [12 ]
Srivastava, Ashok [13 ]
Zaiane, Osmar [14 ]
机构
[1] PredictionWorks Inc, Seattle, WA 98126 USA
[2] Univ Vermont, Dept Comp Sci, Burlington, VT 05405 USA
[3] NeuronWorks Int, Hurstville, NSW 2220, Australia
[4] Yahoo Res, Barcelona, Spain
[5] Univ Technol Sydney, Sydney, NSW 2007, Australia
[6] AT&T Labs, Florham Pk, NJ USA
[7] Carnegie Mellon Univ, Dept Comp Sci, Pittsburgh, PA 15213 USA
[8] Accenture Technol Labs, Chicago, IL 60601 USA
[9] Lucid Commerce, Seattle, WA 98104 USA
[10] Univ Antwerp, Dept Math & Comp Sci, Antwerp, Belgium
[11] Univ Queensland, Dept Math, Brisbane, Qld 4072, Australia
[12] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
[13] NASA, Washington, DC USA
[14] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2E8, Canada
基金
美国国家科学基金会;
关键词
Data mining; cost-benefit analysis; case study;
D O I
10.1142/S021962201240007X
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We report on the panel discussion held at the ICDM'10 conference on the top 10 data mining case studies in order to provide a snapshot of where and how data mining techniques have made significant real-world impact. The tasks covered by 10 case studies range from the detection of anomalies such as cancer, fraud, and system failures to the optimization of organizational operations, and include the automated extraction of information from unstructured sources. From the 10 cases we find that supervised methods prevail while unsupervised techniques play a supporting role. Further, significant domain knowledge is generally required to achieve a completed solution. Finally, we find that successful applications are more commonly associated with continual improvement rather than by single "aha moments" of knowledge ("nugget") discovery.
引用
收藏
页码:389 / 400
页数:12
相关论文
共 50 条