02
Δευ, Δεκ

ERM522: Predictive Analytics in Risk Management

  • Κωδικός / Course Code: ERM522
  • ECTS: 10
  • Τρόποι Αξιολόγησης / Assessment: 2 Assignments (30%), Interactive activities (10%), Final Exam (60%)
  • Διάρκεια Φοίτησης/ Length of Study: Εξαμηνιαία (χειμερινό) / Semi-annual (fall)
  • Κόστος/ Tuition Fees: 500 euro
  • Επίπεδο Σπουδών/ Level: Μεταπτυχιακό/ Postgraduate
  • Προαπαιτούμενα/ Prerequisites: ERM512: Advanced Quantitative Methods for Risk Management 
  • Αναλυτική πληροφόρηση: ERM522_ECTS_2024_Module_Layout.pdf

This Thematic Unit / Module is designed to to introduce students to a range of applications of advanced analytics that are suitable in risk management context. The module emphasizes more on how predictive analytics can be effective tools in reducing risk rather than the theoretical underpinnings of the models.


In the last decade, the amount of data available to organizations has reached unprecedented levels. Companies and individuals who can use this data together with analytics give themselves an edge over the competition. Predictive analytics is transforming risk management as it helps organizations by informing them what is arriving in the future. The Module covers a wide area of models and techniques from simple visual models and extending to statistical and machine learning techniques as well as some basic financial risk models. The approach is to focus on practical and conceptual issues involved in substantive applications of risk management.


The main objective of the module is to train students in employing methodologies and techniques for extracting information from existing data in order to determine patterns and predict future outcomes and trends, with an acceptable level of reliability, including what-if scenarios and risk assessment.


Students develop in depth understanding of the key technologies in data science and business analytics: data mining, machine learning, visualization techniques, predictive modelling, and statistics.


Through the study of proper case studies, students will be able to identify the inputs and outputs involved in each modelling approach and the suitability of the models to specific instances, gain practical, hands-on experience with statistics programming languages and big data tools through coursework, and practical assignments.