Process Mining

2024/2025

Content, progress and pedagogy of the module

PURPOSE

Data storage and data analysis are the key terms in data science, however, a data scientist also needs to understand the operational processes that produce the data, in order to cope with complex scenarios and to correctly apply advanced analysis techniques. This process mining course aims to bridge the gap between data-centric techniques like data mining and machine learning and the traditional process-based models

Learning objectives

Knowledge

The students completing this course get introduced to the basic process model and the analysis techniques that allow to explore their behaviour. Further, different techniques for process discovery will be studied, with a particular focus on event logs that contain noise and/or are incomplete. The students will also learn about conformance testing and alignment between the process model and the real data, as well as techniques for process mining in the large and possible extensions with quantitative aspects like time and probabilities

The list of topics may include:

  • process models like transition systems, automata, workflow nets and business process modelling notation, 

  • basic process analysis techniques like reachability, deadlock detection and soundness checking, 

  • process discovery techniques, event logs, noise and incompleteness and algorithms for process discovery, 

  • advanced process mining techniques, like heuristic mining, genetic mining, and inductive mining

  • conformance checking and alignment as well as mining in the large  

  • mining additional quantitative properties like time, probabilities and decision mining

Skills

  • to explain the process mining methodology and connect it to the data mining counterpart, 

  • to apply the techniques discussed in the course on concrete examples, 

  • to assess and explain the principles behind both the algorithmic part and the conformance and alignment with real data, and 

  • to select and apply the techniques to a concrete process mining case study, possibly with the help of automated tools

Competences

  • to evaluate and reason about different process mining scenarios, and

  •  to develop feasible approaches to process mining of real processes, including the application of available formalisms and tool support

Extent and expected workload

The type of instruction is organised in accordance with the general instruction methods of the programme, cf. § 17.

Exam

Exams

Name of examProcess Mining
Type of exam
Written or oral exam
ECTS5
Assessment7-point grading scale
Type of gradingInternal examination
Criteria of assessmentThe criteria of assessment are stated in the Examination Policies and Procedures

Additional information

Contact: Study Board for Computer Science via cs-sn@cs.aau.dk or 9940 8854

Facts about the module

Danish titleProcess Mining
Module codeDSNDVK203
Module typeCourse
Duration1 semester
SemesterSpring
ECTS5
Language of instructionDanish and English
Empty-place SchemeYes
Location of the lectureCampus Aalborg
Responsible for the module

Organisation

Education ownerMaster of Science (MSc) in Data Science and Machine Learning
Study BoardStudy Board of Computer Science
DepartmentDepartment of Computer Science
FacultyThe Technical Faculty of IT and Design