Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Integration and reuse of data mining in business processes - A pattern-based approach

: Wegener, D.; Rüping, S.

Postprint urn:nbn:de:0011-n-1893550 (642 KByte PDF)
MD5 Fingerprint: 925bec8d44efa5913952c7380bcbd558
Erstellt am: 20.6.2012

International journal of business process integration and management : IJBPIM 5 (2011), Nr.3, S.218-228
ISSN: 1741-8771
ISSN: 1741-8763
Zeitschriftenaufsatz, Elektronische Publikation
Fraunhofer IAIS ()
data mining patterns; business processes; reuse; integration; BPM; CRISP; fraud detection; healthcare; business process management; service oriented architecture; SOA

Today's business applications demand high flexibility in processing information and extracting knowledge from data. Thus, data mining becomes more and more an integral part of operating a business. However, the integration of data mining into business processes still requires a lot of coordination and manual adjustment. This paper aims at reducing this effort by reusing successful data mining solutions. We describe a novel approach to facilitating the integration based on process patterns for data mining and demonstrate that these patterns allow for easy reuse and can significantly speed up the process of integration. We empirically evaluate our approach in a case study of fraud detection in the healthcare domain.