Maximizing Synchronization for Aligning Observed and Modelled Behaviour

Abstract

Conformance checking is a branch of process mining that aims to assess to what degree event data originating from the execution of a (business) process and a corresponding reference model conform to each other. Alignments have been recently introduced as a solution for conformance checking and have since rapidly developed into becoming the de facto standard. The state-of-the-art method to compute alignments is based on solving a shortest path problem derived from the reference model and the event data. Within such a shortest path problem, a cost function is used to guide the search to an optimal solution. The standard cost-function treats mismatches in the model and log as equal. In this paper, we consider a variant of this standard cost function which maximizes the number of correct matches instead. We study the effects of using this cost-function compared to the standard cost function on both small and large models using over a thousand generated and industrial case studies. We further show that the alignment computation process can be sped up significantly in specific instances. Finally, we present a new algorithm for the computation of alignments on models with many log traces that is an order of magnitude faster (in maximizing synchronous moves) compared to the state-of-the-art A* based solution method, as a result of a preprocessing step on the model.

Approximate Computation of Alignments of Business Processes Through Relaxation Labelling

“…Recently, two different approaches have appeared: the work in [3] proposes using binary decision diagrams to alleviate the computation of alignments. The work in [4], which has the goal of maximizing the synchronous moves of the computed alignments, uses a pre-processing step on the model.…”

Conformance checking

“…These optimization functions rely on several types of input. These consist of distance [2,3], manually customizable costs for specific process violations [17], legal moves [16,18], probabilities [26], synchronous moves [7], region theory and state similarity [10]. Furthermore, two approaches implement cost-functions to create alignments which are customized to event monitoring points in a hospital setting to compute optimal alignments [4,25].…”

“…Adriansyah et al [4] present such an event-based fitness measure that counts each non-conforming event and divides them by the total number of events. Third, trace alignments utilize different kinds of cost functions to compute a fitness metric [5,7,14,15,17,20,25,26,33,35,47]. Two declarative ones approach the fitness calculation regarding previously determined business rules [8,12].…”

Structural Computation of Alignments of Business Processes Over Partial Orders

“…Recently, two different approaches from the same authors have appeared; the work in [11] proposes using binary decision diagrams to alleviate the computation of alignments. The work in [12], which has the goal of maximizing the synchronous moves of the computed alignments, uses a pre-processing step on the model.…”

“…Recently, a different focus has been proposed for alignment computation, where the maximization of the synchronous moves is considered [12]. The underlying idea of maximizing synchronous moves is to try to adhere as much as possible to the observed trace, instead of minimizing the penalties assigned to asynchronous moves.…”