Aim of teaching:
The main aim of the course is to enable MSc in Cybersecurity Engineering and MSc in Data Science students to understand the complete process of the practical application of data science: identifying data sources, evaluating data quality, data visualization, decision support, predictive analytics, anomaly detection, the application of artificial intelligence, and the ethical and responsible use of data. The course is application-oriented rather than an algorithm-programming course, with an engineering and decision-support focus. Students learn to formulate real-world problems as data science problems, evaluate data sources and model outputs, interpret dashboards and performance metrics, design simple risk and decision-support concepts, and professionally document, communicate, and audit data-driven systems.
Tematics:
Main topics: practical data science and data-to-decision thinking; the data science project lifecycle and CRISP-DM; problem framing; data sources, data collection, data quality and conceptual data cleaning; data visualisation and dashboard design; descriptive and diagnostic analytics; predictive analytics and risk scoring; machine learning as a decision-support tool and model evaluation; image data, computer vision and AI; time-series data and anomaly detection; generative AI and LLMs; responsible AI, data ethics and data governance; implementation, validation, stakeholder analysis, MVP and pilot projects, user acceptance, operation, maintenance. Methodology: case studies, data-analytical thinking, teamwork, data interpretation, risk analysis, dashboard and decision-support concepts, and professional presentations.