Title: Performance Analysis: Discovering Semi-Markov Models From Event Logs

Speaker: Dr Anna Kalenkova

Summary: Process mining is a well-established discipline of data analysis focused on the discovery of process models from information systems’ event logs. Recently, an emerging subarea of process mining – stochastic process discovery has started to evolve. Stochastic process discovery considers frequencies of events in the event data and allows for more comprehensive analysis. In particular, when durations of activities are presented in the event log, performance characteristics of the discovered stochastic models can be analysed, e.g., the overall process execution time can be estimated. Existing performance analysis techniques usually discover stochastic process models from event data and then simulate these models to evaluate their execution times. We propose analytical techniques for performance analysis allowing for the derivation of statistical characteristics of the overall processes’ execution times in the presence of arbitrary time distributions of events modelled by semi-Markov processes. In the case of what-if analysis the proposed analytical methods can significantly simplify the analysis of process models by providing exact solutions without resorting to simulation.

Biography: Anna Kalenkova got her PhD degree in computer science at Eindhoven University of Technology (TU/e), The Netherlands in 2018. Starting from 2023 she is a lecturer at The School of Computer and Mathematical Sciences, University of Adelaide. Her interests lie in process mining, event data analysis, visual analytics, and information theory. She applies stochastic modelling in process mining to study how stochastic models can be discovered from event data.

WED 10 MAY 16:00-17:00 (AEST, Melbourne Time)

ZOOM MEETING ID: 873 1557 5255; PASSWORD: 778635