Greedy Approach to Compute Alignments of Process Models and Event Logs

In Process Mining, computing alignments is a conformance-checking technique to compare a process model with an event log of the same process to pinpoint difference between how the model would prescribe the process to be executed, and how the event log states the process has been executed. The complexity of this problem is naturally exponential with respect to the size of the model, and benefits can be achieved using divide-and-conquer approaches: the model is decomposed into small fragment for which we can compute alignments. This thesis compares the time to compute alignments using the traditional approaches and our decomposition-based approaches to identify the possible benefits. The results are also compared with different approaches based on process-model decompositions.