English   Danish

2024/2025  KAN-CCMVV1450U  Quantitative Risk Management – An Application of Machine Learning

English Title
Quantitative Risk Management – An Application of Machine Learning

Course information

Language English
Course ECTS 7.5 ECTS
Type Elective
Level Full Degree Master
Duration One Semester
Start time of the course Autumn
Timetable Course schedule will be posted at calendar.cbs.dk
Max. participants 150
Study board
Study Board for cand.merc. and GMA (CM)
Course coordinator
  • Björn Preuss - Department of International Economics, Goverment and Business (EGB)
Main academic disciplines
  • Finance
  • Information technology
  • Statistics and quantitative methods
Teaching methods
  • Blended learning
Last updated on 15-02-2024

Relevant links

Learning objectives
Upon completion of the course, the student should be able to:
  • Identify risk areas that can be modeled with data and explain what is required to do so
  • Assess the limitations of data driven risk management and identify ways how to overcome them if possible
  • Demonstrate different modeling approaches for risk and describe their attached limitations
  • Calculate such risk models in R or Python for simple data examples
  • Discuss the governance element and explain ethical considerations related to such quantitative modeling’s e.g. in a finance application
Course prerequisites
A completed BSc. degree with knowledge about relevant concepts from management, strategy, finance, statistics, and organization studies. Some basic programming skills in R or Python are required. It has to be mentioned that the coding examples in the course will be based on Python but in the examination, both languages are allowed.
Examination
Quantitative Risk Management - An Application of Machine Learning:
Exam ECTS 7,5
Examination form Home assignment - written product
Individual or group exam Individual exam
Size of written product Max. 15 pages
Assignment type Project
Release of assignment Subject chosen by students themselves, see guidelines if any
Duration Written product to be submitted on specified date and time.
Grading scale 7-point grading scale
Examiner(s) One internal examiner
Exam period Winter
Make-up exam/re-exam
Same examination form as the ordinary exam
If the student fails the ordinary exam the course coordinator chooses whether the student will have to hand in a revised product for the re-take or a new project.
Description of the exam procedure

The exam will be an individual written assignment based on a topic/case/application that students can choose. The students will get some guidelines and questions to cover in the exam. It will be a project assignment, and the hand-in paper might not exceed 15 pages excl. appendix.

 

 

 

Course content, structure and pedagogical approach

The global business environment is influenced by many emergent risk factors that can lead to unforeseen events and changes in business dynamics. Besides dramatic changes such as financial crises, political conflicts, competitive disruption, natural disasters, pandemics, etc. some uncertainties can be modeled using modern algorithm-based approaches. This introduces new potentially dramatic threats or challenges but at the same time offers opportunities to be explored and exploited.

 

The use of statistical models in computer algorithms allows computers to make decisions and predictions, and to perform tasks that traditionally require human cognitive abilities. Machine learning is the interdisciplinary field at the intersection of statistics and computer science, which develops such statistical models and computer algorithms. It underpins many modern technologies, such as speech recognition, Internet search, bioinformatics, and computer vision for example Amazon’s recommender system, Google’s driverless car and the most recent imaging systems for cancer diagnosis make use of Machine Learning technology.

 

This course on quantitative risk management with certain elements of Machine Learning will explain how to build systems that learn and adapt using real-world applications to detect and manage risks in a corporate setting. Some topics to be covered include linear regression, logistic regression, deep neural networks, clustering, and so forth. The course will be project-oriented with emphasis placed on writing software scripts of learning algorithms applied to real-world problems, in particular, Credit Risk, Collections Management, and Fraud Detection.

 

Besides the technical elements, the course will touch upon the requirements that are set for an organization to use ML in such highly relevant applications. It will have discussion sessions that touch upon the limitations and necessities for these sorts of models.

 

The course attempts to advance critical thinking on quantitative risk management in open class discussions and group exercises analyzing (often well-known) situations that demonstrate shortcomings and challenges off certain methods. It outlines modern quantitative risk management and considers how leaders can deal (more) effectively with contemporary environments. The shortcomings of current practices are addressed with the intent to develop effective approaches to deal with the risks we face today.

Description of the teaching methods
The course will have the following main elements
- 5 face-to-face lectures focusing on exercises and discussions
- 5 blended learning sessions structured in multiple learning videos and reading material
- Additional self-study and reading material
The course will contain a mix of lectures, exercises, and casework/calculations. It will be taught in a blended learning format which includes; online lectures and side discussion sessions. The class sessions attempt to combine open discussions and active student involvement through coding exercises and discussions. It will utilize a blended learning approach where pre-recorded videos, online lectures, and face-to-face discussions will be combined. Students are expected to work diligently to prepare for class sessions and engage with insights that can benefit the collective learning of the entire class. At the end of the course, students are required to complete an individual written exam report, which provides an opportunity to apply material studied during the course to deal with a self-chosen topic of particular interest. The exam report will be subjected to internal grading that considers the clarity, structure, and supportive evidence displayed in the submitted report concerning the listed learning objectives and course content.
Feedback during the teaching period
Students receive continuous feedback in the sessions where they are asked to apply concepts of Risk Management to problem statements. During class, we discuss concepts, and students are actively involved in the discussion, giving them the opportunity to get direct feedback on their way of thinking about corporate finance theories and concepts.
Throughout the application of quizzes in canvas, the students get after making a quiz direct feedback from the teacher or the system.

The exercises, quizzes, and discussions are linked to some of the learning objectives of this course, meaning that feedback activities can help you familiarize yourself with the assessment method of the course as well as to provide you with a clear indication of the standards expected from your work. Further feedback by teachers is offered in response to questions by individual students or groups. Students are at all times able to reach the teacher by email to ask questions or schedule meetings if needed.
Student workload
lectures and workshops 30 hours
Preparation 136 hours
Exam including preparation 40 hours
Expected literature

 

[1] Aziz, S., & Dowling, M. (2019). Machine learning and AI for risk management. In Disrupting finance (pp. 33-50). Palgrave Pivot, Cham.

[2] Leo, M., Sharma, S., & Maddulety, K. (2019). Machine learning in banking risk management: A literature review. Risks7(1), 29.

[3] Van Liebergen, B. (2017). Machine learning: a revolution in risk management and compliance?. Journal of Financial Transformation45, 60-67.

[4] Chandrinos, S. K., Sakkas, G., & Lagaros, N. D. (2018). AIRMS: A risk management tool using machine learning. Expert Systems with Applications105, 34-48.

[5] Fécamp, S., Mikael, J., & Warin, X. (2019). Risk management with machine-learning-based algorithms. arXiv preprint arXiv:1902.05287.

[6] Dionne, G. (2013). Risk management: History, definition, and critique. Risk management and insurance review16(2), 147-166.

Last updated on 15-02-2024