Applied Data Analysis

Course Description

Welcome to the course “Applied Data Analysis”. In summer semester 2025, the course takes place in a hybrid setting, consisting of on-site lectures at TU Dresden as well as online lectures and e-learning exercises via Zoom.

This practice-oriented module introduces the fundamentals of applied data analysis and provides an overview of relevant concepts, methods, and technologies. The focus here is particularly on the subfield of predictive analytics and the approaches of (supervised) machine learning for creating predictive models. Using a systematic procedure model, the basic steps and principles of predictive modeling are illustrated and underpinned with example approaches.

Learning objectives

• After actively participating in the module, students can describe the fields of application of applied data analysis and business analytics and classify basic technologies, methods and concepts.
• They are able to classify and differentiate between basic concepts, functionalities and principles of predictive modeling and, in particular, machine (supervised) learning.
• Building on this, they have a comprehensive understanding of the structure and functioning of predictive models based on machine learning methods.
• Students are able to explain the basic steps for developing an comprehensive domain and data understanding, for the exploration and preprocessing of data, and for the development and evaluation of machine learning models using a systematic approach.
• Furthermore, they have mastered the fundamental methods and principles of a range of machine learning models and can apply these to various practical examples, as well as evaluate, interpret and critically question the results.
• In addition, they are able to implement data analysis approaches and machine learning models using the Python programming language to address real-world problems.

Course structure

The practice-oriented module consists of lectures to convey conceptual content and an accompanying e-learning exercise in which selected aspects are explored in more depth and implemented using the programming language Python based on real data sets and demonstration examples.

Contents of the lecture units

• Classification of business analytics concepts and related approaches
• (descriptive analysis methods and tools, esp. business intelligence, online analytical processing, data warehousing, reporting, dashboards)
• Predictive models and differentiation from explanatory models
• Different types of machine learning
• Supervised learning (classification and regression tasks)
• Procedure models in the area of business analytics (e.g. CRISP-DM)
• Domain and data understanding
• Data preprocessing and feature engineering
• Model training with selected machine learning methods (e.g. linear/logistic regression, decision trees, ensemble methods, artificial neural networks)
• Model evaluation

Contents of the e-learning units

• Data exploration and visualization
• Data preprocessing and feature engineering
• Model development and training with selected machine learning models
• Model evaluation and diagnosis

Course information

 Schedule (lecture + exercise)