Details
| Original language | English |
|---|---|
| Pages (from-to) | 1-55 |
| Number of pages | 90 |
| Journal | Journal of Financial Econometrics |
| Volume | 23 |
| Issue number | 2 |
| Publication status | Published - 10 Mar 2025 |
Abstract
Keywords
- diverging, machine learning, risk, premia, stock risk
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Financial Econometrics, Vol. 23, No. 2, 10.03.2025, p. 1-55.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Diverging Roads
T2 - Theory-Based vs. Machine Learning-Implied Stock Risk Premia
AU - Grammig, Joachim
AU - Hanenberg, Constantin
AU - Schlag, Christian
AU - Sönksen, Jantje
PY - 2025/3/10
Y1 - 2025/3/10
N2 - We assess financial theory-based and machine learning methods to quantify stock risk premia and investigate the potential of hybrid strategies. In the low signal-to-noise environment of a one-month investment horizon, we recommend to rely on a theory-based strategy that exploits the information in current option prices, especially if the risk premium estimate is to be updated at a high frequency. At the one-year horizon, the theory/option-based strategy and an ensemble of neural networks, two notably different methodologies, perform comparably well. A random forest can improve on the theory-based method, provided that a sufficiently long training period is used. In an effort to connect the opposing philosophies, we identify the use of a random forest to account for the approximation errors of the theory-based approach towards measuring stock risk premia as a promising hybrid strategy. It combines the advantages of two diverging roads in the finance world.
AB - We assess financial theory-based and machine learning methods to quantify stock risk premia and investigate the potential of hybrid strategies. In the low signal-to-noise environment of a one-month investment horizon, we recommend to rely on a theory-based strategy that exploits the information in current option prices, especially if the risk premium estimate is to be updated at a high frequency. At the one-year horizon, the theory/option-based strategy and an ensemble of neural networks, two notably different methodologies, perform comparably well. A random forest can improve on the theory-based method, provided that a sufficiently long training period is used. In an effort to connect the opposing philosophies, we identify the use of a random forest to account for the approximation errors of the theory-based approach towards measuring stock risk premia as a promising hybrid strategy. It combines the advantages of two diverging roads in the finance world.
KW - diverging
KW - machine learning
KW - risk
KW - premia
KW - stock risk
U2 - 10.1093/jjfinec/nbaf005
DO - 10.1093/jjfinec/nbaf005
M3 - Article
VL - 23
SP - 1
EP - 55
JO - Journal of Financial Econometrics
JF - Journal of Financial Econometrics
SN - 1479-8409
IS - 2
ER -