DocumentCode :
2372544
Title :
AHP Construct Mining Component strategy applied for data mining process
Author :
Zhang, Yun ; Li, Weihua
Author_Institution :
Sch. of Comput., Northwestern Polytech. Univ., Xi´´an, China
fYear :
2012
fDate :
23-25 March 2012
Firstpage :
591
Lastpage :
595
Abstract :
AHP Construct Mining Component (ACMC), which is a new term, is an enhancement of applicable structure for multidimensional and multi-level complex dataflow. ACMC is applied into data mining framework and different processing components with the purpose are improvement on numerous aspects in multiply level. ACMC provides not only an integrated platform to support different processing components with comprehensive and systemic methodology but also provides controllable strategy for whole processing. The instances of KPI (key performance indicator) and CSF (critical success factor) are the key points and foundation of the whole data mining structure. Mode-Refresh and Model-Evaluation are recognized as engines of the data mining machine. Influencing factor that come from these engines will influence decision constrictions. ACMC supports combination of different mining component from strategy level, tactical level to abstractive level, and then provide the successful model component for the whole data mining processing. ACMC is a new direction of the decision of KDD (Knowledge Discovery in Database).
Keywords :
data flow computing; data mining; database management systems; decision making; AHP construct mining component strategy; abstractive level; critical success factor; data mining framework; data mining machine; data mining process; data mining structure; integrated platform; key performance indicator; knowledge discovery in database; mode-refresh; model-evaluation; multidimensional complex dataflow; multilevel complex dataflow; strategy level; tactical level; Analytical models; Association rules; Business; Data models; Databases; Predictive models;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Science and Technology (ICIST), 2012 International Conference on
Conference_Location :
Hubei
Print_ISBN :
978-1-4577-0343-0
Type :
conf
DOI :
10.1109/ICIST.2012.6221714
Filename :
6221714
Link To Document :
بازگشت