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.

Doubt in question 4

The 4th Question in this year's challenge titled "Differences across years" has asked to characterize the difference of processes as a particular instantiation of concept drift. What does "a particular instantiation of concept drift" mean in this context?


  • As stated in the question, you can consider batches of data belonging to the same year (2015, 2016 and 2017).
    In each year, there are changes in the process. Some may be very obvious (documents have been replaced by other documents), others may be more subtle (e.g., the process owner may have found means to improve the process).

    We would be interested in a formal analysis of these changes.

    Consider for example the three problems stated on page 2 of this paper:

    Solving any of these problems for these year-wise changes would be very interesting.

    Another interesting aspect to look at could be the impact of changes across years for the other questions. E.g., how is a predictive model for undesired outcomes (first question) valid in the presence of concept drift.

  • Thank you for your help
Sign In or Register to comment.