CAS Machine Learning for Advanced Portfolio and Risk Management

After completing the programme, participants will be able to:

• Develop, test, and validate machine learning models for investment strategies and risk management.

• Apply data-driven approaches to portfolio optimisation.

• Navigate regulatory, ethical, and technical challenges in ML projects.

• Collaborate effectively across disciplines with data scientists, portfolio managers, and compliance professionals.

With its strong ties to the finance industry and close collaboration with leading experts, this CAS offers immediate value to practitioners looking to integrate machine learning into their workflows in a meaningful way. It stands out in the Swiss continuing education landscape and helps drive innovation in the financial sector.

This programme is designed for:

• Portfolio and risk managers aiming to develop or enhance data-driven models for portfolio construction and risk management.

• Investment analysts and finance professionals looking to integrate machine learning into forecasting, risk assessment, and alpha generation.

• Quants and data scientists with technical skills who want to deepen their understanding of ML applications in finance.

• IT and tech specialists in financial institutions working on the implementation and optimisation of ML-driven systems in trading, investment, and risk.

• Experienced business and strategy consultants seeking to better understand the potential of ML and AI in enabling data-informed decision-making within financial organisations.

• Project leads managing innovative ML-based financial solutions who want to navigate the specific challenges of ML projects in finance and integrate them successfully into existing processes.

• Finance and business professionals with a strong entrepreneurial mindset, looking to implement and scale AI/ML-driven strategies in their own organisations.

Module: Foundations of Machine Learning in Finance

Upon completing the programme, participants will:

• Gain a solid foundation in Python as a tool for data analysis and financial application.

• Understand the core principles of supervised and unsupervised learning, as well as feature engineering tailored to financial datasets.

• Become familiar with key ML models for portfolio construction and risk management, including Markowitz optimisation and factor modelling.

• Be aware of the importance of data quality, security, and regulatory compliance in financial applications.

• Be equipped to design data-driven portfolio strategies and critically assess machine learning-based decision models.

Module: Advanced Machine Learning Applications

Upon completing the programme, participants will:

• Be familiar with advanced ML techniques such as Lasso, SVMs, decision trees, and neural networks for financial applications.

• Gain deep insights into ML-based risk models, including Value at Risk, stress testing, and anomaly detection.

• Be able to design, backtest, and evaluate algorithmic trading strategies using relevant performance metrics.

• Understand model validation techniques and how to stress-test and enhance the robustness of ML models.

• Explore cutting-edge research topics, particularly Explainable AI (XAI), to improve model transparency and interpretability.

• Benefit from an expanded professional network across finance, tech, and machine learning communities.

• Expanded leadership opportunities in the financial sector.

• Specialization in managing AI projects.

• Enhanced career prospects as a Data Scientist or Risk Manager.

• Potential to drive innovation within corporate environments.

In-person teaching with a variety of methods such as discussions, presentations, exercises, and case studies.

Use of exchange and networking with leaders from practice.