Introduction to Algorithmic Data AnalysisLaajuus (4 cr)

Objective

Learning outcomes: Student understands: what kind of problems can be solved using algorithmic data analysis; principles, prerequisites, and algorithmic foundations of the most common data analysis methods; prerequisites and goals of data mining and machine learning; the workflow of algorithmic data analysis Student knows how to choose the correct approach (descriptive vs. predictive) and to choose the correct method, considering also the scalability, from the most common ones. Student can use the common data analysis methods, and knows how to analyse the results.

Content

Different phases of data analysis. Basic concepts in descriptive and predictive data analysis. Mining of association rules and frequent itemsets. Common clustering algorithms. Basics of graph analysis. Decision trees, naïve Bayes classifier and linear classifiers. Kernel trick. Testing the significance of the results. Detecting and analysing anomalies. Privacy and fairness in data-analysis. Efficient implementations.

Qualifications

Introductory course in statistics (or similar skills), Data Structures and Algorithms I (or similar skills)

Materials

T