Data mining model management to support real-time business intelligence in service-oriented architectures

Use of predictive models for making business-critical decisions is on the rise. However, serious challenges remain on managing data mining models and integrating them with business services using service-oriented architectures (SOA) to provide real-time Business Intelligence (BI). These challenges include model aging, management scalability, timely-communication among parties on model changes, semantic gap on interpreting models, and business process integration. We describe a data mining model management system that addresses these challenges to support sustainable and operationalized BI.

[1]  Riddhiman Ghosh,et al.  Mashups for semantic user profiles , 2008, WWW.

[2]  Torben Bach Pedersen,et al.  RiTE: Providing On-Demand Data for Right-Time Data Warehousing , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[3]  Bing Liu,et al.  Managing large collections of data mining models , 2008, CACM.

[4]  Joseph Antonik,et al.  Decision Management , 2007, MILCOM 2007 - IEEE Military Communications Conference.

[5]  Philip A. Bernstein,et al.  Model management 2.0: manipulating richer mappings , 2007, SIGMOD '07.

[6]  Riddhiman Ghosh,et al.  Providing session management as core business service , 2007, WWW '07.

[7]  Christian S. Jensen,et al.  Web Services Business Process Execution Language , 2009, Encyclopedia of Database Systems.

[8]  S. Sumathi,et al.  Data Mining in Customer Value and Customer Relationship Management , 2006 .

[9]  Leesa Robinson,et al.  Model management , 1994 .