Examination arrangement

Course content

Data science comprises a significant variety of methods and technologies for aggregating and analyzing data. The aim of most courses in AI is to understand the finer details of the methodological aspects. This course, however, is aimed at developing knowledge of, skills in, and competence of the most used methods. The course exploits the fact that many business-relevant, practical problems applications of data science do not require the most sophisticated methods. Moreover, most of the value-generating solutions should focus on the overall development of the solution, and not only on the data analysis part. Which problem to solve, which business goals to measure, and how to continuously monitor the proposed solution are major parts of the overall process that are hardly talked about. This course specifically focuses on the practical applications of these elements of data-driven analysis projects.

Learning outcome

Knowledge: The candidate will establish deep knowledge about the development cycle of data science projects. Skills: The candidate will gain solid skills in setting up and configuring data science tools. The candidate will develop good skills in identifying what methods are appropriate for what type of problems. Competence: The candidate will establish competence in the application of selected data science methods to address business and strategic challenges.

Learning methods and activities

The course consists of lectures and project work. The students need to complete a group-based project that is to be presented as well as an individual assignment. In the group project, the students go through realistic, problem-oriented analytics of the data. The group project is to develop practical skills in configuring the relevant tools/technologies, pre-processing data, and conducting the analytics. The individual assignment discusses the group project in light of relevant literature from the course curriculum.

Compulsory assignments

• Individual repot

Further on evaluation

The portfolio consists of a group report and a recorded presentation of the work done.

An individual report is mandatory and needs to be approved in order to hand in the group report.

There will be no re-sit.

Recommended previous knowledge

It is recommended to have some background and hands-on experience with different data analysis methods (with or without Machine learning). Since the goal of the course is to make you proficient in the overall development cycle of a data science project, we do not explicitly cover different data analysis methods (except one introductory lecture on Machine Learning). So, to contribute to the group project, it will benefit to have some experience in data analysis methods.

Required previous knowledge

None

Course materials

Provided throughout the semester