Read out

Guest Talk: Evidence-Based Conformance Checking for Event Logs with Coarse-grained Timestamps

Dr. Henrik Leopold

Date/Time: 07.05.2018, 11:00

Loca­tion: D2.2.094 


Confor­man­ce-che­cking tech­ni­ques are an effi­cient means to detect unde­sired beha­vior. They provide the possi­bi­lity to auto­ma­ti­cally detect diffe­rences between actual beha­vior and desired beha­vior by compa­ring an event log with a process model. However, a key assump­tion of tradi­tional confor­man­ce-che­cking tech­ni­ques is that all events in the event log are labeled with timestamps that allow to infer the event order. Unfor­t­u­n­a­tely, this is not always the case in prac­tice. One of the most common issues is that timestamps are too cour­se-grained. They might, for instance, reveal the day but not the exact time of an event. For such event logs, tradi­tional confor­man­ce-che­cking tech­ni­ques are not able to produce useful results. Reco­gni­zing this limi­ta­tion, we propose an approach that uses infor­ma­tion from the entire event log to derive the most likely execu­tion sequence for a given case without a clear event order. We use a large event log from the health­care domain to illus­trate that our approach indeed allows conduc­ting more accu­rate confor­mance checking and provides addi­tional analytic insights.


Dr. Henrik Leopold is an Assis­tant Professor at the Depart­ment of Computer Science at the Vrije Univer­siteit Amsterdam (VU). Before joining the VU in February 2015, he held posi­tions as an Assis­tant Professor at the WU Vienna and as a post­doc­toral rese­arch fellow at the Humboldt Univer­sity of Berlin. In July 2013, he obtained a PhD degree in Infor­ma­tion Systems from the Humboldt Univer­sity of Berlin. His doctoral thesis received the German TARGION Award 2014 for the best disser­ta­tion in the field of stra­tegic infor­ma­tion manage­ment. His rese­arch is mainly concerned with the inter­play between infor­ma­tion systems and busi­ness processes. He is parti­cu­larly inte­rested in how to leverage tech­no­logy from the field of arti­fi­cial intel­li­gence (such as machine learning and natural language proces­sing) to analyze and support the execu­tion of busi­ness processes. He has published over 60 rese­arch papers and arti­cles, among others, in Data & Know­ledge Engi­nee­ring, Deci­sion Support Systems, IEEE Tran­sac­tions on Soft­ware Engi­nee­ring, and Infor­ma­tion Systems.

Back to overview