Lecturers

prof.dr.ir. W.M.P. van der Aalst (responsible lecturer)

Type of examination:

- Assignments

- Written (3 hours)

The mark will be based on an assignment (4 points) and a written exam (6 points, 3 hours). The assignment is mandatory, but expires after the first written exam, i.e., it is not possible to just retake the written exam or just the assignment. The exam in the interim period covers the whole material and can be used to obtain the full 10 points. See the study guide for details.

Type of education:

7 weeks lecture 2 hours per week

Prior knowledge

- 2ID05 - Datamodeling and databases (recommended)

- 2II05 - Business Information Systems (recommended)

Learning objectives

After taking this course students should:

- have a detailed understanding of the entire process mining spectrum and be able to relate process mining techniques to other analysis techniques for business processes,

- master various representational biases for process mining (subclasses of Petri nets, structured process models, C-nets, etc.),

- understand and apply advanced process discovery techniques based on regions and genetic algorithms,

- be able to discuss all four conformance dimensions (replay fitness, precision, generalization, and simplicity), provide metrics for these dimensions, and apply conformance checking using models and logs,

- be able to reason about the strengths and weaknesses of existing process mining algorithms and critically evaluate new ones.

Contents

Process mining provides a new means to improve processes in a variety of application domains. There are two main drivers for this new technology. On the one hand, more and more events are being recorded thus providing detailed information about the history of processes. On the other hand, in most organizations there is a need to improve process performance (e.g., reduce costs and flow time) and compliance (e.g., avoid deviations or risks). This advanced course on process mining teaches students the theoretical foundations of process mining and exposes students to real-life data sets to understand challenges related to process discovery, conformance checking, and model extension.

The course will cover various advanced process discovery techniques, i.e., techniques based on region theory and genetic algorithms. One needs to be able to understand such techniques, apply them, and know their strengths and weaknesses.

The course will also cover conformance checking techniques covering all four conformance dimensions: replay fitness, precision, generalization, and simplicity. A key element is the notion of alignments linking observed to modeled behavior.

Process mining techniques will not be limited to control-flow and will also include other perspectives such as time (bottleneck analysis), resources (social network analysis), and data (decision mining).

Besides learning theoretical concepts, students will be exposed to event data from a variety of domains, including hospitals, insurance companies, governments, high-tech systems, etc. The assignment will either focus on the analysis of such data sets or on focusing on a particular process mining problem.

Note that the bachelor course Business Process Intelligence (2IIE0,2IIF0) introduces process mining at an introductory level. This course is not required as prior knowledge. However, students can benefit from this bachelor course to already have an initial understanding of process mining and seeing more elementary process mining algorithms.

Course material