Learning objectives: |
On successful completion of this course, students are able to:
- Evaluate different data analytics processes and their differentiating key aspects.
- Understand the steps of the CRoss-Industry Standard Process for Data Mining (CRISP-DM) for data analytics applications.
- Apply selected techniques and algorithms to a data set from a task-oriented perspective using the CRISP-DM.
- Use external data sources in analyses to derive new insights.
- Relate the potential negative impact of data quality problems to each step of the CRISP-DM process.
- Assignments: Students need to complete a minimal number of five out of six assignments to pass the course. One repair assignment is available, if students have missed two assignments in total. It is not possible to repair multiple assignments.
To have successfully finished INFOWO is a strong recommendation for enrollment in this course.
- Mid-term exam (50%)
- Final exam (50%)
Applied data analytics is a multidisciplinary field where you will learn insights needed to make sense of data, research, and observations from everyday life.
You will learn how to apply a data-driven approach to problem solving, but will not only learn about tools, methods, and techniques, or the latest trends, but also more generic insights: why do certain approaches work, why the field is so popular, what common mistakes are made, and so on.
The lectures will provide the theoretical background of how a data analytics process should be performed according to industry standards.
Furthermore, we discuss an overview of popular data analytics techniques to help match techniques with information needs, including applications of text mining and data enrichment.
- Two 2-hour lectures per week
- One 2-hour tutorial per week