Value demonstration of embedded analytics for front office applications
Erik Nijkamp, Martin Oberhofer, Albert Maier · 2009
Abstract: Users offront office applications such as call center or customer support applications make millions and millions of decisions each day without analytical support. For example, if asupport employee gets anew support ticket and needs to decide how much time should be used for problem resolution and which measures should be taken, this is done without analytical insight. As aresult, companies cannot optimize their front office departments because analytical insight derived in Business Intelligence (BI) Systems isnot available tousers of these applications. Our demo shows how toimprove aCustomer Relationship Management (CRM) System [Lin01] by embedding analytics in an“in context ” and “on demand” fashion without requiring any BI System skills. “In context ” means that only analytics relevant for decision making onthe current UIscreen is made available. “On demand ” means that the user has the information accessible in “mouse-over” events, i.e. the user decides when toconsume which portion of the analytical information. This avoids being flooded with information not needed. The underlying implementation uses UIMA [GS04] to determine the context. Real-time lookup services for the delivery of the analytic insight are dynamically bound to the application UI. Inthe demo we will show the system atwork and explain the architecture, the underlying technologies, and the algorithms used for the embedded analytics. Thesystemhas been builtinthe context ofabachelor thesis.