作者: Joos C. A. M. Buijs , Boudewijn F. van Dongen , Wil M. P. van der Aalst
DOI: 10.1007/978-3-642-33606-5_19
关键词: Generalization 、 Quality (business) 、 Machine learning 、 Artificial intelligence 、 Event (computing) 、 Measure (mathematics) 、 Computer science 、 Simplicity 、 Process modeling 、 Business process discovery 、 Work in process
摘要: Process discovery algorithms typically aim at discovering process models from event logs that best describe the recorded behavior. Often, quality of a algorithm is measured by quantifying to what extent resulting model can reproduce behavior in log, i.e. replay fitness. At same time, there are many other metrics compare with terms precision and which generalizes log. Furthermore, several exist measure complexity irrespective