Using Meta-learning to Recommend Process Discovery Methods

Process discovery methods have obtained remarkable achievements in Process Mining, delivering comprehensible process models to enhance management capabilities. However, selecting the suitable method for a specific event log highly relies on human expertise, hindering its broad application. Solutions based on Meta-learning (MtL) have been promising for creating systems with reduced human assistance. This paper presents a MtL solution for recommending process discovery methods that maximize model quality according to complementary dimensions. Thanks to our MtL pipeline, it was possible to recommend a discovery method with 92% of accuracy using light-weight features that describe the event log. Our experimental analysis also provided significant insights on the importance of log features in generating recommendations, paving the way to a deeper understanding of the discovery algorithms.

[1]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Event Logs Containing Infrequent Behaviour , 2013, Business Process Management Workshops.

[2]  Manuel Mucientes,et al.  ProDiGen: Mining complete, precise and minimal structure process models with a genetic algorithm , 2015, Inf. Sci..

[3]  Jan Mendling,et al.  Metrics for Process Models: Empirical Foundations of Verification, Error Prediction, and Guidelines for Correctness , 2008, Lecture Notes in Business Information Processing.

[4]  Marlon Dumas,et al.  Split miner: automated discovery of accurate and simple business process models from event logs , 2019, Knowledge and Information Systems.

[5]  Massimo Mecella,et al.  Automated Discovery of Process Models from Event Logs: Review and Benchmark , 2017, IEEE Transactions on Knowledge and Data Engineering.

[6]  Boudewijn F. van Dongen,et al.  Process mining: a two-step approach to balance between underfitting and overfitting , 2008, Software & Systems Modeling.

[7]  Wil M. P. van der Aalst,et al.  Workflow mining: discovering process models from event logs , 2004, IEEE Transactions on Knowledge and Data Engineering.

[8]  Søren Debois,et al.  Entropy as a Measure of Log Variability , 2019, Journal on Data Semantics.

[9]  Sylvio Barbon Junior,et al.  Towards Proximity Graph Auto-configuration: An Approach Based on Meta-learning , 2020, ADBIS.

[10]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Event Logs - A Constructive Approach , 2013, Petri Nets.

[11]  Boudewijn F. van Dongen,et al.  Quality Dimensions in Process Discovery: The Importance of Fitness, Precision, Generalization and Simplicity , 2014, Int. J. Cooperative Inf. Syst..

[12]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  A meta-learning approach for selecting image segmentation algorithm , 2019, Pattern Recognit. Lett..

[13]  Bart Baesens,et al.  A multi-dimensional quality assessment of state-of-the-art process discovery algorithms using real-life event logs , 2012, Inf. Syst..

[14]  Sylvio Barbon Junior,et al.  Evaluation Goals for Online Process Mining: A Concept Drift Perspective , 2020, IEEE Transactions on Services Computing.

[15]  Sander J. J. Leemans,et al.  Scalable Process Discovery with Guarantees , 2015, BMMDS/EMMSAD.

[16]  Wil M. P. van der Aalst,et al.  Reviving Token-based Replay: Increasing Speed While Improving Diagnostics , 2019, ATAED@Petri Nets/ACSD.

[17]  Wil M. P. van der Aalst,et al.  Conformance checking of processes based on monitoring real behavior , 2008, Inf. Syst..

[18]  C. Humby,et al.  Process Mining: Data science in Action , 2014 .

[19]  Edson Emílio Scalabrin,et al.  Process mining techniques and applications - A systematic mapping study , 2019, Expert Syst. Appl..

[20]  Kaiyong Zhao,et al.  AutoML: A Survey of the State-of-the-Art , 2019, Knowl. Based Syst..

[21]  Sylvio Barbon Junior,et al.  Evaluating Trace Encoding Methods in Process Mining , 2020, DataMod@CIKM.

[22]  Ilia Bider,et al.  ENTERPRISE, BUSINESS-PROCESS AND INFORMATION SYSTEMS MODELING , 2009, EMMSAD 2009.

[23]  Boudewijn F. van Dongen,et al.  Replaying history on process models for conformance checking and performance analysis , 2012, WIREs Data Mining Knowl. Discov..

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Marlon Dumas,et al.  Metaheuristic Optimization for Automated Business Process Discovery , 2019, BPM.

[26]  Josep Carmona,et al.  A Fresh Look at Precision in Process Conformance , 2010, BPM.

[27]  Wil M. P. van der Aalst,et al.  Genetic process mining: an experimental evaluation , 2007, Data Mining and Knowledge Discovery.

[28]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Incomplete Event Logs , 2014, Petri Nets.

[29]  Wil M. P. van der Aalst,et al.  A Rule-Based Approach for Process Discovery: Dealing with Noise and Imbalance in Process Logs , 2005, Data Mining and Knowledge Discovery.