Relative Performance Persistence of Financial Forecasting Models and Its Economic Implications

36 Pages Posted: 8 Jul 2016

See all articles by Eduard Baitinger

Eduard Baitinger

FERI Trust GmbH

Christian Fieberg

City University of Applied Sciences

Thorsten Poddig

University of Bremen

Date Written: July 7, 2016

Abstract

This paper addresses the issue of model selection risk by examining whether a model's past performance in forecasting expected returns provides an indication of its future forecasting performance. For this purpose, we implement a wide range of different forecasting models and then apply the Aiolfi-Timmermann methodology for relative performance persistence measurement. We find no evidence of performance persistence in forecasting models at the top end of the historical forecasting performance rankings. Economic consequences of this purely statistical study are subsequently quantified by an out-of-sample asset allocation exercise. Simulating an asset allocator, who selects ex ante return forecasting models based on their ex post performance, we show that investors should make portfolio decisions based on forecasting models from the middle of the historical forecasting performance rankings.

Keywords: model selection risk, financial forecasting, performance persistence, dimension-reduction, kernel regression, pattern recognition

Suggested Citation

Baitinger, Eduard and Fieberg, Christian and Poddig, Thorsten, Relative Performance Persistence of Financial Forecasting Models and Its Economic Implications (July 7, 2016). Journal of Risk, Forthcoming, Available at SSRN: https://ssrn.com/abstract=2805997

Eduard Baitinger

FERI Trust GmbH ( email )

Rathausplatz 8-10
Bad Homburg v.d.H, 61348
Germany

Christian Fieberg (Contact Author)

City University of Applied Sciences ( email )

Werderstr. 73
Bremen, DE Bremen 28199
Germany

Thorsten Poddig

University of Bremen ( email )

Universitaetsallee GW I
Bremen, D-28334
Germany

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

Paper statistics

Downloads
0
Abstract Views
770
PlumX Metrics