Analysis of the models discovered by Genetic and Heuristic Miner
Hi,
I am working on http://data.3tu.nl/repository/uuid:cdf3ba31-291d-468d-9712-3a58ac6da3fc log.
Following are three models discovered by Alpha, Heuristic and Genetic miners. When possible, can anyone help me with the following :
1. Why are those black squares in the models discovered by Heuristic and Genetic Miner ?
2. When trying to replay the log, the wizard asks me for a final marking. How do I decide which one should be the final marking ?
Thanks in advance !!
Regards,
Shital
Answers
-
Dear Shital,
Thank you for your question.
1. Those 'black squares' in a Petri net are silent transitions. They are not observable (e.g. do not correspond to an activity) but are used to distribute tokens as required. In the example of the heuristics model it takes the token produced by A and makes if available for B and C or B, C and D.
2. The initial marking is how the model starts, e.g. where are tokens. For the petri net discovered by the Heuristics miner this is the place that serves as input to activity A. The final marking it the marking that should be acchieved to know that the process has finished. In the example of the heuristics model this is the place that is the output of activity G. Only this place should contain a token, none of the other places.
Advanced remark: note that the process models discovered by the Heuristics miner is not sound, e.g. tokens can be left behind.
I hope this answers your question Shital!
Joos Buijs
Senior Data Scientist and process mining expert at APG (Dutch pension fund executor).
Previously Assistant Professor in Process Mining at Eindhoven University of Technology
Howdy, Stranger!
Categories
- 1.6K All Categories
- 45 Announcements / News
- 224 Process Mining
- 6 - BPI Challenge 2020
- 9 - BPI Challenge 2019
- 24 - BPI Challenge 2018
- 27 - BPI Challenge 2017
- 8 - BPI Challenge 2016
- 68 Research
- 1K ProM 6
- 393 - Usage
- 287 - Development
- 9 RapidProM
- 1 - Usage
- 7 - Development
- 54 ProM5
- 19 - Usage
- 187 Event Logs
- 32 - ProMimport
- 75 - XESame