Syllabus
Building on previous sessions:
- Regression I builds the basics, Regression II introduces model tuning (forward/backward variable selection in multiple regression, non-linear transformations, logistic regression)
- ML I builds the basics, ML II introduces feature engineering, ensemble models, …
Summary
This module introduces students to the methods, technologies, and governance of modern data analytics across descriptive, predictive, and prescriptive approaches. It builds a comprehensive understanding of the data analytics process—from data structuring and preparation to exploratory data analysis, analytical modeling, and decision support. The module combines conceptual foundations and hands-on analytical practice using Python, pandas, and scikit-learn. It progresses from structured transactional data (data warehouses, OLAP, data mining) to big and unstructured data (text, social, streaming). Emphasis is placed on the fit between data types, analytical models, and decision purposes, as well as the ability to design, evaluate, and govern analytical systems in organizations.
Course policies
- Group assignment requirement: The course includes a mandatory group assignment. This assignment cannot be completed individually and requires active collaboration with your group.
- On-site participation: The group assignment requires your physical presence on site. Remote-only completion is not possible for this course component.
- Enrollment and attendance expectation: Enrollment implies regular course participation. Being enrolled without attending is not acceptable; students who cannot attend should cancel their enrollment.
Learning objectives
Knowledge After completing the module, students will be able to:
- Differentiate between descriptive, predictive, and prescriptive analytics approaches.
- Describe architectures for data warehousing and big data processing, with reference to the underlying data modeling concepts.
- Explain fundamental concepts of data analytics, and its role in data-driven organizations.
Skills Students will be able to:
- Select appropriate analytical methods for transactional or non-transactional data, and for descriptive, predictive, and prescriptive analysis tasks.
- Apply analytical methods to real-world datasets, including structuring, transforming, and visualizing data. This also involves training models, evaluating performance, and interpreting analytical results for decision-making.
- Implement analytical procedures in Python, using standard data science libraries (pandas, scikit-learn, matplotlib).
Competence Upon successful completion, students will be able to:
- Design analytics solutions aligned with business goals and governance principles.
- Integrate analytical technologies into organizational decision-making processes
- Assess the operational and strategic implications of data analytics in organizations.