Predicting Investor Behaviour in European Bonds Markets - A Machine Learning Approach (Presentation Slides)

Posted: 25 Oct 2019

See all articles by Martin Hillebrand

Martin Hillebrand

XU Exponential University

Bastien Winant

affiliation not provided to SSRN

Marko Mravlak

European Stability Mechanism

Peter Schwendner

Zurich University of Applied Sciences

Date Written: September 20, 2019

Abstract

We are predicting primary market demand of investors in ESM bond issues using regression trees. Using a bagged tree methodology, we already get useful forecasts. Using feature impact, we characterize the behaviour of different investor types. On some single investors, the direction of demand change can be forecasted. Forecast quality is expected to improve considerably when enhancing database and refining technology.

Keywords: Bond markets, Investor behaviour, Order books, European Stability Mechanism, Market access

JEL Classification: G11, G23, D53, E44

Suggested Citation

Hillebrand, Martin and Winant, Bastien and Mravlak, Marko and Schwendner, Peter, Predicting Investor Behaviour in European Bonds Markets - A Machine Learning Approach (Presentation Slides) (September 20, 2019). Available at SSRN: https://ssrn.com/abstract=3457081

Martin Hillebrand (Contact Author)

XU Exponential University ( email )

August-Bebel-Str. 26-53
Potsdam, 14482
Germany

Bastien Winant

affiliation not provided to SSRN

Marko Mravlak

European Stability Mechanism ( email )

6a Circuit de la Foire Internationale
Luxembourg, L-1347
Luxembourg

Peter Schwendner

Zurich University of Applied Sciences ( email )

School of Management and Law
Gertrudstrasse 8
Winterthur, CH 8401
Switzerland

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
122
PlumX Metrics