To prevent spam users, you can only post on this forum after registration, which is by invitation. If you want to post on the forum, please send me a mail (h DOT m DOT w DOT verbeek AT tue DOT nl) and I'll send you an invitation in return for an account.

Event log sources

Can anyone help me find a source for exampler event log of an unstructured/ spaghetti process?

Comments

  • Hi,

    I think that in this collection you will find several interesting real life event logs:
    http://data.3tu.nl/repository/collection:event_logs_real

    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
  • Thanks JBuijs,

    I've already surfed all these sources...but how about the examples available through chapter 11 and 12 of the book entitled :"process mining: discovery, conformance and enhancement of business processes"
    Are they available somewhere else?
  • As far as I know these event logs are not public.
    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
  • Hello

    Can anyone help me find a source for exampl event logs L1, L2, L3 in the paper "On the Role of Fitness, Precision, Generalization and Simplicity in Process Discovery" from Buijs
     

  • Hi Janan,

    I believe the data is available here:
    http://data.4tu.nl/repository/uuid:bd8fcc48-5bf3-480e-8775-d79d6c700e90

    Please reference the data as a regular publication in your references if you use it in a paper :)

    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
  • Hi dear Buijs thank you to relay.  I have referenced some of part my thesis.  thank you.


  • but I have a problem in calculate generalization. I am going use your formula to measure calculation but there is some thing difference. my process model is term of petri net with transition and place but your model is term of process tree. how can I use your formula for petri net? I have sent attach file.

    Thank you



  • Hi Janan,

    I think that my metric is easy to apply on Petri nets: just use transitions as your nodes (e.g. ignore the places) and count how often they are executed.

    You know how often they are executed after you have calculated alignments.
    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
  • Hi dear buijs

    Thank you. I have sent a example of generalization. my supervisor is so interesting to see your idea about this example. would you please take a short look and give me your suggestion? Thank you  

  • Hi Janan,

    I did a quick check and your results seem alright.
    However, please note that you can't/shouldn't just use the event log, but the alignments and then count only the synchronous moves. This is different than counting the number of times the activity occurred in the event log. E.g. trace <a,c,h,g,d,f,a> would have no occurrence count for either h or g depending on the alignment!
    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
  • I am so thanks full. I am finishing my thesis. after finish I will send it to you. I have referenced  your event log L0 ,generalization metric and your result ETM miner from prom.
  • the latest my comparison approaches is ETM miner to Fitness, Persian, Generalization and simplicity. But ETM seems give me different results on different models.  which of them can I use in my thesis to show best result of these four metric on Petri net?
  • Hi dear Buijs

    in your paper you calculated generalization on alpha ++ algorithm and give 0.889. but I have used alignment between model and log but my value is 0.880. would you please to take short look in my alignment?  

    Thank you

  • Hi Janan,

    It could be that either you or me made a rounding error. I would consider the difference minimal and it won't really impact your findings I believe.
    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
Sign In or Register to comment.