392123 Introduction to Data Mining (V) (WiSe 2025/2026)

The course covers foundational methods of data mining, explorative data analysis, and visualization. The focus is on educational data (so-called 'educational data mining' or 'learning analytics'). Example methods are:

• statistical tests, esp. t-tests and signed rank test
• Principal Component Analysis
• k-Means Clustering
• Item Response Theory
• Bayesian Knowledge Tracing
• Variational Auto Encoders
• Generative Models

The core skills taught are:

• critical, analytical thinking about models and applications of data mining
• how to design models (formalization, following modeling arguments)
• how to implement models (in Python)
• debugging and interpreting models when applied to data

Requirements for participation, required level

Useful prior knowledge: Neural Networks, Linear Algebra, Probability Theory
Relations to: Information Visualization, Introduction to Machine Learning, Pattern Recognition, Unsupervised Machine Learning, Generative AI

Bibliography

• Baker, Yacef (2009): The State of Educational Data Mining in 2009: A Review and Future Visions. https://jedm.educationaldatamining.org/index.php/JEDM/article/view/8
• Abdi, Williams (2010): Principal component analysis. https://doi.org/10.1002/wics.101
• Jain (2010): Data clustering: 50 years beyond K-means. https://doi.org/10.1016/j.patrec.2009.09.011
• Baker (2001): The basics of item response theory. https://files.eric.ed.gov/fulltext/ED458219.pdf
• Abdelrahman, Wang, Nunes (2022): Knowledge Tracing: A Survey. https://doi.org/10.1145/3569576
• Paaßen, Dywel, Fleckenstein, Pinkwart (2022): Sparse Factor Autoencoders for Item Response Theory. https://files.eric.ed.gov/fulltext/ED624123.pdf