Performance Evaluation of Inductive Miner for Internship Program Workflow
Article Sidebar
Main Article Content
Abstract
Modern organizations involve a high number of activities in their operations, which can be very complex. Process model is used to simplify these complex activities. Various algorithms for discovering process models have been developed in process mining. Process mining can extract important information from each activity in obtained cases. There are three process mining algorithms commonly used: Alpha, Heuristic Miner, and Inductive Miner. Each of the algorithms has its own characteristics. This paper compares these algorithms for the Internship Program. Based on the obtained evaluation, Alpha algorithm can't describe the process based on PKL event log well. It is because loop processes exist. It is also shown that the PKL process is not implementing the SOP well yet. On the other hand, Heuristic Miner neglects minor processes which do not frequently happen and does not describe it in the process model. Inductive miner combines the working principle of Alpha Miner and Heuristic Miner. Overall, the process model that is formed uses the Alpha algorithm which is closest to reality because it has a fitness of 0.96.
Downloads
Article Details
[2] F. M. Maggi, C. Di Francescomarino, M. Dumas, and C. Ghidini, “Predictive Monitoring of Business Processes,” 2013, [Online]. Available: http://arxiv.org/abs/1312.4874.
[3] S. Huda, R. Sarno, and T. Ahmad, “Increasing accuracy of process-based fraud detection using a behavior model,” Int. J. Softw. Eng. its Appl., vol. 10, no. 5, pp. 175–188, 2016, doi: 10.14257/ijseia.2016.10.5.16.
[4] A. Awad, G. Decker, and M. Weske, “Efficient compliance checking using BPMN-Q and temporal logic,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 5240 LNCS, pp. 326–341, 2008, doi: 10.1007/978-3-540-85758-7-24.
[5] E. Files and D. S. Models, Discovering Simulation Models - Tutorial, vol. 34, no. 3. 2010.
[6] A. Rozinat, R. S. Mans, M. Song, and W. M. P. van der Aalst, “Discovering colored Petri nets from event logs,” Int. J. Softw. Tools Technol. Transf., vol. 10, no. 1, 2008, doi: 10.1007/s10009-007-0051-0.
[7] M. Song and W. M. P. van der Aalst, “Towards comprehensive support for organizational mining,” Decis. Support Syst., vol. 46, no. 1, pp. 300–317, 2008, doi: 10.1016/j.dss.2008.07.002.
[8] D. Rahmawati, M. A. Yaqin, and R. Sarno, “Fraud detection on event logs of goods and services procurement business process using Heuristics Miner algorithm,” in 2016 International Conference on Information Communication Technology and Systems (ICTS), 2016, pp. 249–254, doi: 10.1109/ICTS.2016.7910307.
[9] Y. A. Effendi and R. Sarno, “Discovering process model from event logs by considering overlapping rules,” Int. Conf. Electr. Eng. Comput. Sci. Informatics, vol. 2017-Decem, no. September, pp. 19–21, 2017, doi: 10.1109/EECSI.2017.8239193.
[10] R. Ghawi, “Process Discovery using Inductive Miner and Decomposition,” no. October, 2016, [Online]. Available: http://arxiv.org/abs/1610.07989.
[11] A. K. Alves de Medeiros, A. J. M. M. Weijters, and W. M. P. van der Aalst, “Genetic process mining: A basic approach and its challenges,” Bus. Process Manag. Work. (BPM 2005), vol. 3812, no. task C, pp. 203–215, 2006, doi: 10.1007/11678564_18.
[12] R. Sarno, Kartini, W. A. Wibowo, and A. Solichaha, “Time based Discovery of parallel business processes,” Proceeding - 2015 Int. Conf. Comput. Control. Informatics Its Appl. Emerg. Trends Era Internet Things, IC3INA 2015, pp. 28–33, 2016, doi: 10.1109/IC3INA.2015.7377741.
[13] D. Informatika, F. Teknik, U. T. Madura, and D. Informatika, “a More Efficient Deterministic Algorithm in Process,” vol. 14, no. 3, pp. 971–995, 2018.
[14] R. Sarno, Y. A. Effendi, and F. Haryadita, “Modified Time-Based Heuristics Miner for Parallel Business Processes,” IRECOS (International Rev. Comput. Software), vol. 11, no. 3, pp. 249–260, 2016, doi: https://doi.org/10.15866/irecos.v11i3.8717.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.