On 5 and 6 November 2026 Erasmus University Rotterdam, the University of Geneva, and Università della Svizzera Italiana will jointly organise the 4th edition of the FinEML (Financial Econometrics Meets Machine Learning) Conference. The conference will be held at the University of Geneva, Geneva, Switzerland.
- Date
- Thursday 5 Nov 2026, 09:00 - Friday 6 Nov 2026, 18:00
- Type
- Conference
- Location
University of Geneva, Uni Mail, Boulevard du Pont-d’Arve 40, CH-1211 Geneva 4, Switzerland
Organising committee
- Fabio Trojani
- Olivier Scaillet
- Tony Berrada
- Ines Chaieb
- Patrick Gagliardini
- Loriano Mancini
- Paul Schneider
- Anastasija Tetereva
- Alberto Quaini
- Maria Grith
- Mariia Artemova
- Onno Kleen
Speakers
Confirmed keynote speakers are: Peter Bühlmann (ETH Zürich), Christa Cuchiero (University of Vienna) and Kay Giesecke (Stanford University).
Moreover, FinEML will host one of the invited lectures by the Society for Financial Econometrics (SoFiE). This year, the invited lecturer is Christian Gouriéroux (University of Toronto, Toulouse School of Economics).
The Invited Lecture Series was launched in 2024 in Montreal, with Robert Engle and Lars Peter Hansen delivering the inaugural lectures.
Topics
Submissions on the following topics are welcome:
- Asset Pricing: Novel econometric and machine learning approaches for asset pricing, including risk factor discovery, portfolio optimization, and advanced modeling of the stochastic discount factor.
- Big Data: Factor models and sparse methods tailored to large-scale, high-dimensional financial data.
- Forecasting: Novel forecasting techniques covering time series analysis, predictive modeling, and risk assessment in dynamic financial markets.
- Macro Finance: Econometrics and machine learning methods for macro-financial analyses, encompassing yield curve forecasting, text-based insights from central bank communications, projection models, and nowcasting techniques.
- Option Pricing: Data-driven advances in implied volatility forecasting, option return predictability, tail risk estimation, and extracting forward-looking investor beliefs.
- Theoretical Machine Learning: Focusing on learning theory, optimization techniques, complexity analysis, and statistical guarantees that underpin machine learning algorithms with applications in finance
Important Dates
- Call for papers submission deadline: 22 June 2026
- Conference dates: 5 and 6 November 2026
Call for papers
Sponsors
