Portfolio item number 1
Published:
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Published:
Short description of portfolio item number 2
publications
Multi-period Growth-at-Risk Forecasting with Recurrent Neural Network
Working Paper, 2024
We propose to forecast multi-horizon Growth-at-Risk using flexible dynamic sequence models combining many-to-many recurrent neural networks with an objective function that guarantees non-crossing of quantile estimates.
Recommended citation: Kooiker, S., Hoesch, L., & Schaumburg, J. (2024). Multi-period Growth-at-Risk Forecasting with Recurrent Neural Network. Working Paper.
Nonparametric Time-Varying Granger Causality
Working Paper, 2025
A procedure that integrates an exponentially weighted moving average version of the Diks-Panchenko test with EWMA local density estimators to assess Granger causality in dynamic environments.
Recommended citation: Kooiker, S. (2025). Nonparametric Time-Varying Granger Causality. Working Paper.
Self-driving neural networks for term structure modeling
Working Paper, 2026
We propose a factor model with time-varying loadings for term structure modeling, specifying the loadings as neural networks that evolve over time using a self-driving updating scheme based on past forecast errors.
Recommended citation: Kooiker, S., van Brummelen, J., Schaumburg, J., & Zamojski, M. (2026). Self-Driving Neural Networks for Term Structure Modeling. Working Paper.
Download Paper
The Forecasting Grand Prix: Self-Driving Neural Networks for Inflation Prediction
Working Paper, 2026
We propose a time-varying neural network framework for macroeconomic forecasting in which the weights and biases of a neural network evolve over time using a self-driving updating scheme
Recommended citation: Kooiker, S., van Brummelen, J. & Schaumburg, J. (2026). The Forecasting Grand Prix: Self-Driving Neural Networks for Inflation Prediction. Working Paper.
Download Paper
talks
Multi-period Growth-at-Risk Forecasting with Recurrent Neural Network
Published:
Presentation of Growth-at-Risk forecasting paper at the Italian Econometrics Association workshop for PhD students. This presentation included a formal discussant.
Multi-period Growth-at-Risk Forecasting with Recurrent Neural Network
Published:
Poster presentation of Growth-at-Risk forecasting paper at the annual National Econometrics Study Group meeting at Erasmus University Rotterdam.
Multi-period Growth-at-Risk Forecasting with Recurrent Neural Network
Published:
Presentation of joint work with Lukas Hoesch and Julia Schaumburg on Growth-at-Risk forecasting with recurrent neural networks at the International Symposium on Forecasting.
Nonparametric Time-Varying Granger Causality
Published:
Presentation of single-authored paper on nonparametric time-varying Granger causality at the CFE-CMS conference at King’s College London.
Econometric Game 2025 Finalist
Published:
Finalist in the Econometric Game 2025 at the University of Amsterdam. Three-day competition project on grid congestion forecasting in Germany.
Dynamic Nelson Siegel Model with Time-Varying Neural Factor Loadings
Published:
Presentation of joint work on dynamic Nelson-Siegel models with neural factor loadings at the FinEML Conference at Erasmus University Rotterdam.
Nonparametric Time-Varying Granger Causality
Published:
Presentation of single-authored paper on nonparametric time-varying Granger causality at the International Association for Applied Econometrics conference at the University of Torino.
Dynamic Nelson Siegel Model with Time-Varying Neural Factor Loadings
Published:
Presentation of third paper at the International Symposium on Forecasting conference in Beijing, China, in the second year of the PhD.
Dynamic Nelson Siegel Model with Time-Varying Neural Factor Loadings
Published:
Presentation of joint work on dynamic Nelson-Siegel models with neural factor loadings at the ECB Conference on Forecasting Techniques. This presentation included a formal discussant.
teaching
Course Coordinator - Business Statistics Courses
PhD Teaching Assistant, Vrije Universiteit Amsterdam, School of Business and Economics, 2023
As a PhD candidate, I coordinate two large-scale courses with over 600 students each in the Business Statistics program. This role involves organizing teaching activities, managing teaching assistants, developing course materials, and ensuring smooth delivery of the courses.
Thesis Supervision
MSc/BSc Thesis Supervision, Vrije Universiteit Amsterdam, School of Business and Economics, 2023
Supervising Bachelor and Master students during their thesis projects in Econometrics, Data Science, and related fields. Topics focus on machine learning, time series forecasting, and econometric methods.