Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/213939 
Erscheinungsjahr: 
2020
Schriftenreihe/Nr.: 
University of Tübingen Working Papers in Business and Economics No. 130
Verlag: 
University of Tübingen, Faculty of Economics and Social Sciences, Tübingen
Zusammenfassung: 
We assess financial theory-based and machine learning-implied measurements of stock risk premia by comparing the quality of their return forecasts. In the low signal-to-noise environment of a one month horizon, we find that it is preferable to rely on a theory-based approach instead of engaging in the computerintensive hyper-parameter tuning of statistical models. The theory-based approach also delivers a solid performance at the one year horizon, at which only one machine learning methodology (random forest) performs substantially better. We also consider ways to combine the opposing modeling philosophies, and identify the use of random forests to account for the approximation residuals of the theory-based approach as a promising hybrid strategy. It combines the advantages of the two diverging paths in the finance world.
Schlagwörter: 
stock risk premia
return forecasts
machine learning
theorybased return prediction
JEL: 
C53
C58
G12
G17
Persistent Identifier der Erstveröffentlichung: 
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
1.16 MB





Publikationen in EconStor sind urheberrechtlich geschützt.