The student will, for example,
- identify existing openly accessible data sources (including interfaces) and tools to develop data skills
- explain what insights can be obtained from different data such as text
- utilize different visuals for different uses such as control charts for identifying exceptions, line charts for predictions and AI visuals (i.e., artificial intelligence visuals) for identifying influencers
- utilize automated machine learning tools (such as RapidMiner Go) to create models (such as classifiers) and take advantage of the predictions provided by the models
- create a data model and, if necessary, combine different data sets / tables (or queries) in order to utilize the views produced by the algorithms and create dashboards that utilize the data in different data sets
- identify various executable documents (such as Google Colab) and scripts encoded in the Python programming language when processing data
Insights (i.e., meaningful information) are generated from the data by utilizing libraries of programming languages or by using various ready-made software - learn how to automatically produce prediction models and quick insights from data, for example, to help draw attention to deviations and trends. On the basis of various automatically generated models and quick insights, it is possible to form questions and identify variables in the data that should be taken into account, for example, in feature engineering - learn to describe data variables and evaluate the usability of data. In addition, learn how to transform data and combine different data sets to make intentional analyzes and dashboards.
|Modes of study
lectures 24 h (12*2 h), tutorials 12 h (6*2 h), lecture exam (4 h) and independent work 90 h (5 cp), 65 h (4 cp).
The principles of flipped learning are applied in multimodal teaching, i.e., the student becomes familiar with the given material independently and conducts for assignments. Student learning is supported by online lectures and online tutorials - lectures focus on answering what and why questions, tutorials focus on answering how-to questions and assessing exercise assignments, and evolving to use the various communication and behavioral skills needed to design information systems.
Lecture material and other material are in the Moodle learning environment. Lecture-specific topic summary videos are produced by the teacher in Moodle. The course uses a variety of tools such as Power BI Desktop (a desktop application) and RapidMiner Go (a browser application). The university offers the possibility to use a virtual desktop, (https://studentuef.sharepoint.com/sites/heimo_fi/palvelut/ohjelmistot-ja-lisenssit/Sivut/Ohjelmat-kotikoneisiin.aspx), where you can install the software required for the course, if they cannot be used as browser applications
The assignments (40 points, if 4 cp; 60 points, if 5 cp) and the lecture exam (30 points) are evaluated. The lecture exam must receive at least 15 points.
The grades (0–5) are determined as follows (4 cp): 1 - min 15 points, 2 - min 25 points, 3 - min 35 points, 4 - min 45 points, 5 - min 55 points. The grades (0–5) are determined as follows (5 cp): 1 - min 25 points, 2 - min 35 points, 3 - min 45 points, 4 - min 55 points, 5 - min 65 points.
Preferably the following courses of computer science: Introduction to Computing and Programming I - Elementary Programming.
This course is open to everyone
The teaching language is Finnish. Some of the course material is in English, such as the articles selected for the course material and the definitions of vocabularies as well as tool instructions. ---