Prof. Dr. Thomas Krabichler

IFL Institut für Finance und LawKompetenzzentrum Banking und Finance

+41 58 257 12 18thomas.krabichler@ost.ch

Thomas is a professor at the campus in St. Gallen. His research focuses on applications of machine learning in finance. He is an associate member of the «Interdisciplinary Centre for Artificial Intelligence (ICAI)» and holds a doctoral degree from ETH Zürich in mathematics. His collaboration with Josef Teichmann was honoured with the «Swiss Risk Award» in 2020. Previously, he worked for about ten years as a quant specialist in the financial industry. In this role, he was mainly engaged in the valuation and hedging of financial derivatives for major investment banks in the UK, France and Switzerland.

Area of Expertise

  • Asset-Liability-Management (ALM)
  • Automated Market Making (AMM)
  • Credit Risk
  • Deep Learning
  • Derivatives
  • Financial Modelling
  • Hedging
  • Illiquidity
  • Investment Strategies
  • Machine Learning in Finance
  • Mathematical Finance
  • Model Validation
  • Programming
  • Quantitative Analyses
  • Reinforcement Learning
  • Risk Management
  • Risk Quantification
  • Scenario Generation
  • Structured Products
  • Term Structure Modelling
  • Valuation

Education

2012 - 2017 Doctor of Sciences, Stochastic Finance Group, ETH Zürich
2010 - 2013 Advanced Studies in Actuarial Science (Actuary SAA), ETH Zürich
2007 - 2009 Mathematics Teaching Certificate, ETH Zürich
2004 - 2009 Master of Science in Mathematics, ETH Zürich
1999 - 2003 Matura, Kantonsschule am Burggraben, St. Gallen

Professional Experience

2023 - present Professor, Eastern Switzerland University of Applied Sciences, St. Gallen (OST)
2020 - 2023 Lecturer & Quant Researcher, Eastern Switzerland University of Applied Sciences, St. Gallen (OST)
2018 - 2020 Lecturer & Quant Researcher, Lucerne University of Applied Sciences and Arts (HSLU - IFZ)
2010 - 2018 Quantitative Finance & Risk Consultant, PricewaterhouseCoopers AG (PwC)
2009 - 2010 Trading Desk Quant (Internship), Credit Suisse AG

Teaching Experience

  • Analysis
  • Analytics
  • Credit Risk
  • Machine Learning
  • Mathematical Finance
  • Optimisation
  • Probability Theory
  • Quantitative Modelling
  • Risk Management
  • Statistics

Projects

2022 - 2023 Establishment and Liquidation of a Long-Term Fund
2020 - present Automated Collateral Management Systems (53978.1 INNO-ICT, 55591.1 IP-ICT)
2020 - present Bespoke Data Analytics
2020 - present Goal-Based Investing
2020 - present Optimisation of Gas Storages and Illiquid Portfolios
2019 - present Deep ALM
2019 - 2021 Optimisation of Hydroelectric Power Plants
2019 - 2020 Predictive Credit Analytics with Neural Networks
2019 - 2020 Quicktest of Credit Capacity for SMEs (37920.1 INNO-SBM)
2018 - 2020 Reinforcement Learning for Pricing & Hedging of Derivatives

Memberships

  • Associate Member of the «ICAI Interdisciplinary Centre for Artificial Intelligence»
  • Fully Qualified Actuary within the Swiss Association of Actuaries («Sektion Aktuare SAV»)
  • Member of the Data Innovation Alliance
  • Member of the Swiss Risk Association (SRA)
  • Academic Partner of the CQF Institute

Editorials and Reviewing

  • Independent reviewer of scientific journal articles in the field of mathematical finance

Awards

  • Swiss Risk Award 2020 together with Josef Teichmann (ETH)

Peer-Reviewed Journal Articles and Conference Proceedings

  • Brönnimann, W., Egloff, P., and Krabichler, T. (2024, Preprint 2023). Automated Market Makers and their Implications for Liquidity Providers. Digital Finance. Vol. 6. No. 3. pp. 573-604. https://doi.org/10.1007/s42521-024-00117-0.
  • Englisch, H., Krabichler, T., Müller, K. J., and Schwarz, M. (2023, Preprint 2022). Deep Treasury Management for Banks. Frontiers in Artificial Intelligence. Vol. 6. https://doi.org/10.3389/frai.2023.1120297.
  • Hou, S., Krabichler, T., and Wunsch, M. (2022, Preprint 2021). Deep Partial Hedging. Journal of Risk and Financial Management. Vol. 15. No. 5. Article 223. https://doi.org/10.3390/jrfm15050223.
  • Krabichler, T., and Wunsch, M. (2023, Preprint 2021). Hedging Goals. Financial Markets and Portfolio Management. https://doi.org/10.1007/s11408-023-00437-y.
  • Curin, N., Kettler, M., Kleisinger-Yu, X., Komaric, V., Krabichler, T., Teichmann, J., and Wutte, H. (2021). A deep learning model for gas storage optimization. Decisions in Economics and Finance. Vol. 44. pp. 1021–1037. https://doi.org/10.1007/s10203-021-00363-6.
  • Krabichler, T., and Teichmann, J. (2023, Preprint 2020). A Case Study for Unlocking the Potential of Deep Learning in Asset-Liability-Management. Frontiers in Artificial Intelligence. Vol. 6. https://doi.org/10.3389/frai.2023.1177702.
  • Krabichler, T., and Teichmann, J. (Preprint 2020). A constraint-based notion of illiquidity. Submitted, arXiv:2004.12394.
  • Krabichler, T., and Teichmann, J. (2024, Preprint 2020). The Jarrow & Turnbull setting revisited. International Journal of Theoretical and Applied Finance. https://doi.org/10.1142/S0219024923500322.
  • Krabichler, T. (2019). Reinforcement Learning for Pricing & Hedging of Derivatives - A Simplified Showcase. IFZ Working Paper Series. No. 0008. https://doi.org/10.5281/zenodo.2590928.
  • Krabichler, T. (2019). If only there were no liquidity constraints. IFZ Working Paper Series. No. 0007. https://doi.org/10.5281/zenodo.2590926.
  • Krabichler, T. (2019). If only we knew the drift. IFZ Working Paper Series. No. 0006. https://doi.org/10.5281/zenodo.2590924.

Books and Research Monographs

  • Krabichler, T. (2018). Term Structure Modelling Beyond Classical Paradigms - An FX-like Approach. Dissertation. ETH Research Collection. https://doi.org/10.3929/ethz-b-000199168.

Professional Journals and Newspaper

Beiträge
- Egloff, P., and Turnes, E. (2023). Blockchain in der Finanzwelt. Verlag SKV.
- Lux, W., Krabichler, T., and Gehrig, M. (2023). Unternehmerische Resilienz und Resilienzverlust. Newsletter «Finanz- und Rechnungswesen» (April 2023), WEKA Business Media AG.
- Millius, T. (2022). Derivate 2.0. Interview, LEADER – Das Ostschweizer Unternehmermagazin (June 2022).
- Borkert, S. (2022). Künstliche Intelligenz kann nicht alles. Press Article, St. Galler Tagblatt (15.03.2022).
- Bechtiger, P., and Spring, R. (2022). Orientierung statt Moneypulierung. Verlag SKV. (Machine Learning in Financial Planning).
- Krabichler, T. (2019). Künstliche Intelligenz in der Finanzbranche - eine Utopie? IFZ Retail Banking Blog.
- Cuchiero, C., Larsson, M. and Svalutto-Ferro, S. (2018). Polynomial jump-diffusions on the unit simplex. Annals of Applied Probability. Vol. 28, No. 4, pp. 2451–2500.
- Golnaraghi, M. (2018). Climate Change and the Insurance Industry: Taking Action as Risk Managers and Investors. The Geneva Association.

Teaching related publications

  • Krabichler, T. (2022). Risikokalkül für eine Leasing-Gesellschaft. Case Study & Teaching Notes, Open Education Platform (OEP) for Management Schools.
  • Krabichler, T. (2019). New Frontiers in Quantitative Risk Management (Updated Version). https://doi.org/10.5281/zenodo.5094917.

Presentations

  • Kann KI mein Geld anlegen? Data Science Talks, University of Hamburg (D), Podcast, https://open.spotify.com/show/5T02RSRfup08oR2c5SEHit?si=2e38a1f31e984252.
  • Exploring the Dynamics of Liquidity Pools: A Mathematical Approach. (2024). Seminario al Dipartimento di Scienze Economiche, Università di Verona (I).
  • Automated Market Makers and their Implications for Liquidity Providers. (2024). Digital Assets Switzerland, Webinar.
  • A Parametric Spot and Vol Surface Model for Equities. (2024). ETH Stochastic Finance Group, Friday Seminar, Zürich (CH).
  • Ramifications of Deep Hedging. (2023). Research Seminar, Faculty of Mathematics, Informatics and Natural Sciences, University of Hamburg (D), Webinar.
  • Automated Market Makers and their Implications for Liquidity Providers. (2023). Stochastics, Statistics, Machine Learning and their Applications to Sustainable Finance & Energy Markets, Wolfgang Pauli Institute (WPI), Vienna (A).
  • Automated Market Makers and their Implications for Liquidity Providers. (2023). 3rd Oxford - ETH Workshop on Mathematical & Computational Finance, University of Oxford (UK).
  • Deep Asset-Liability-Management. (2022). 7th European COST Conference on AI in Industry & Finance, Winterthur (CH).
  • Deep Treasury Management. (2022). KI Erfahrungsaustausch Schweizer Inlandbanken, Webinar.
  • ML in Finance. (2022). Public Lecture, ICAI, St. Gallen (CH).
  • Einführung in Künstliche Intelligenz und Machine Learning in Finance. (2022). Guest Lecture, Certificate Program Blockchain & Fintech, University of Liechtenstein (FL).
  • Künstliche Intelligenz im Spannungsfeld zwischen Mensch und Maschine. (2022). SGKB Konjunktur- und Trendforum Horizonte, St. Gallen (CH), Live Broadcast.
  • What Can SMEs Learn from «ML in Finance»? (2021). CSEMnext, Alpnach (CH).
  • Balance Sheet Optimisation: Vom Bauchgefühl zur Wissenschaft mit AI und ML. (2021). BANKINGCLUB-Online-Forum, Panel Discussion, Köln (D), Webinar.
  • Prescriptive Analytics and Artificial Intelligence. (2021). Guest Lecture, CAS Digital Controlling, IFZ – Institute of Financial Services Zug (CH).
  • Deep Asset-Liability-Management. (2021). COST Fintech and Artificial Intelligence in Finance (FinAI), Webinar.
  • Datenbasierte Anwendungen aus der Praxis. (2021). Guest Lecture, Executive MBA HSG, University of St. Gallen (CH).
  • Rare Events in Financial Modelling. (2021). Data Innovation Alliance: ML-Clinic Expert Group Meeting, Berne (CH).
  • Machine Learning in Finance. (2021). Advisory Board Meeting «Banking East», St. Gallen (CH).
  • Machine Learning in Finance. (2021). Guest Lecture, EMBA, Solvay Brussels School of Economics and Management (B), Webinar.
  • Machine Learning for Pension Funds. (2021). Strategy workshop of a Swiss investment committee, Switzerland (CH).
  • A Deep Learning Model for Gas Storage Optimisation. (2021). Energy Finance Italia 6 Workshop, University of Brescia (I), Webinar.
  • A Deep Learning Model for Gas Storage Optimisation. (2021). SIAM Conference on Financial Mathematics and Engineering, Philadelphia (U.S.), Webinar.
  • Two Showcases of Deep ALM. (2021). SRA Chapter Event: New Frontiers in Data Analytics for Risk and Asset Management, Webinar.
  • Predictive Technologies for Better Business Lending. (2020). Professional Risk Managers' International Association (PRMIA), Singapore, Webinar.
  • Deep Replication of a Runoff Portfolio. (2020). ETH Stochastic Finance Group, Webinar.
  • New Frontiers in Quantitative Risk Management. (2019). IFZ Fintech Colloquium, Rotkreuz (CH).
  • Dynamic Financial Analyses with Reinforcement Learning. (2019). Expert meeting of an international insurance company, Switzerland (CH).
  • Machine Learning in Finance. (2019). Data Science Fundamentals, University of St. Gallen (CH).
  • Deep ALM. (2019). Minisymposium on Mathematical Finance in the age of Machine Learning, ÖMG Conference, Dornbirn (A).
  • Deep ALM. (2019). FPWZ Seminar, University of Padova (I).
  • Credit Risk Management. (2019). Board meeting of a Swiss retail bank, Switzerland (CH).
  • The Transformation of Treasury/ALM to Deliver Optimised Performance Management. (2019). Finastra Universe, Panel Discussion, Frankfurt (D).
  • Reinforcement Learning in Quant Finance: An Introduction for Non-Financial Experts. (2018). Swiss Data Alliance: ML-Clinic Expert Group Meeting, Schweizerische Mobiliar, Berne (CH).
  • A Joint Modelling Framework for Credit and Liquidity Risk. (2018). Workshop of the Freiburg-Strasbourg Research Group on Financial and Actuarial Mathematics, Freiburg Institute for Advanced Studies (D).
  • Term Structure Modelling Beyond Classical Paradigms. (2017). Doctoral Defence, ETH Zürich (CH).
  • The Jarrow & Turnbull Setting Revisited. (2017). 5th Imperial - ETH Workshop on Mathematical Finance, Imperial College London (UK).
  • Term Structure Modelling in the Presence of Multiple Yield Curves. (2016). Challenges in Mathematical Finance, University of Cape Town (ZA).
  • Term Structure Modelling in the Presence of Multiple Yield Curves. (2015). 3rd Imperial - ETH Workshop on Mathematical Finance, Imperial College London (UK).

Entrepreneurial resilience to increase crisis capability

Project

In times of crisis, it becomes clear which companies are resilient, survive the crisis or even use it as an opportunity for something new. Unfortunately, it also becomes clear that many companies fail to do so. The question arises as to what the former do differently or better. The Entrepreneurial Resilience research project addressed precisely this question.