Navigation auf uzh.ch
Navigation auf uzh.ch
CAS in Data Science and AI for Risk Analysis |
|
Study Structure |
Hybrid |
Duration |
6-9 months |
Qualification |
Certificate of Advanced Studies UZH in Data Science and Artificial Intelligence for Risk Analysis(15 ECTS Credits) |
Target Audience |
This program is designed for professionals with a scientific background who wish to deepen their technical expertise in data science and artificial intelligence, with a focus on risk analysis for finance and insurance. Requirements: university degree, preferably in sciences or engineering field as well as finance and economics, and at least two years of professional experience in finance, banking, insurance or related fields. Basic programming knowledge is needed. A Python Foundation Course is offered as a pre-course (videos). |
Fees |
CHF 10'750.– |
Information |
Prof. Delia Coculescu Department of Mathematical Modeling and Machine Learning |
|
|
delia.coculescu@uzh.ch |
Description |
Grounded in a quantitative risk management framework, the curriculum develops a rigorous statistical and mathematical toolkit and then connects it to contemporary machine learning, deep learning, and carefully scoped generative AI workflows for risk work. Core concepts, such as the definition and measurement of risk, risk pricing, risk aggregation, and capital allocation, appear as foundational elements upon which the AI and machine learning components are built. In the applications studios, we focus on emerging risks. Familiarity with coding – as a prerequisite – is expected and can be acquired in a distinct module (a pre-course) offered yearly, before the CAS program start. Participants will also explore critical topics like model interpretability, and ethical AI. Through a blend of lectures, labs, case studies, and a capstone project, the program ensures that graduates are prepared to develop and implement innovative, data-driven solutions for challenges arising in complex risk environments, such as ones in the insurance or financial industry. Learning outcomes Participants will: – Master machine learning and deep learning techniques relevant to finance and insurance. – Choose and validate statistical/ML models appropriate for insurance/finance problems. – Design solutions for emerging risks (cyber, climate, systemic/liquidity risks) using scenarios and data. – Address ethical, regulatory, and security challenges in data science and AI for fiannce and insurance. – Build a complete risk modelling solution (data, methodology, validation and communication) on a realistic problem, in the capstone project. |
Dates |
Program start: March 2027 Registrations opening: 1 November 2026 |
