Efficient unsupervised event context detection

for event log clustering, outlier detection, and pre-processing. We recently developed a technique to detect the context of events from an event log in an efficient way through sub-graph matching. This allows to identify events and parts of event logs which are similar or different to each other, allowing to cluster traces, detect outliers, and improve event log quality, as illustrated in this Demo video. The objective of this assignment is to improve the efficiency of the matching algorithm and the quality of the results through graph summarization and data mining techniques.

Contact: Dr. Dirk Fahland.

Leave a Reply