5 ECTS credits
|Language of instruction
Autumn, period I.
After completing this course, student can recognize data types and perform required pre-processing steps before further analysis:
- Student can design and implement a data collection process
- Student can combine data from different sources
- Student can normalize and transform data, and handle missing or incorrect values
- Student can ensure generalizability of the results
Course provides good ability to start Master’s Thesis or graduate studies. Topics at the course include data mining process in general level, data gathering and different data types, quality and reliability of the data, data preparation including the processing of missing values, outliers, and privacy issues, combination of signals from several sources, utilization of data bases in data mining process, and normalization and transformation of data and interdependence of the observations and their distributions. Additionally, topics concerning the generality of the results are covered, as well as, the principles of data division, for example, train-test-validate, cross-validation and leave-one-out methods.
|Mode of delivery
Lectures, independent work, group work
|Learning activities and teaching methods
16 h lectures, 16 h exercises, independent studying.
The course is suitable for Master level students in Computer science and engineering study programmes, for minor subject studies or for doctoral students.
|Prerequisites and co-requisites
031021P Probability and Mathematical Statistics or similar
|Recommended optional programme components
The course is an independent entity and does not require additional studies carried out at the same time.
|Recommended or required reading
Lecture hand-out and exercise material will be provided. The course book will be announced in the beginning of the course. The material is mostly in English.
|Assessment methods and criteria
Weekly pre-lecture assignment + exercise submissions, and final exam. Half of the grade will be based on the submissions and half on the final exam.
Read more about assessment criteria at the University of Oulu webpage.
Numerical grading scale 1-5; zero stands for a fail.
|Working life cooperation
/>Towards Data Mining 521156S:3