Optimal asset allocation and nonlinear return predictability from the dividend-price ratio

Fabrizio  Ghezzi; Anindo Sarkar; Thomas Quistgaard Pedersen; Allan Timmermann

doi:10.1007/s10479-024-06332-7

Optimal asset allocation and nonlinear return predictability from the dividend-price ratio

Fabrizio Ghezzi, Anindo Sarkar, Thomas Quistgaard Pedersen, Allan Timmermann

Department of Economics and Business Economics

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

We study non-linear predictability of stock returns arising from the dividend-price ratio and its implications for asset allocation decisions. Using data from five countries — U.S., U.K., France, Germany and Japan — we find empirical evidence supporting non-linear and time-varying models for the equity risk premium. Building on this, we examine several model specifications that can account for non-linear return predictability, including Markov switching models, regression trees, random forests and neural networks. Although in-sample return regressions and portfolio allocation results support the use of non-linear predictability models, the out-of-sample evidence is notably weaker, highlighting the difficulty in exploiting non-linear predictability in real time.

Original language	English
Journal	Annals of Operations Research
Volume	346
Issue	1
Pages (from-to)	415-445
Number of pages	31
ISSN	0254-5330
DOIs	https://doi.org/10.1007/s10479-024-06332-7
Publication status	Published - Mar 2025

Keywords

Asset allocation
Dividend-price ratio dynamics
Dynamics and predictability of stock returns
Machine learning
Nonlinear return predictability

Access to Document

10.1007/s10479-024-06332-7

https://link.springer.com/article/10.1007/s10479-024-06332-7?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20241030&utm_content=10.1007/s10479-024-06332-7

Cite this

@article{be002d0491cf43dcb17d95503a4f62a7,

title = "Optimal asset allocation and nonlinear return predictability from the dividend-price ratio",

abstract = "We study non-linear predictability of stock returns arising from the dividend-price ratio and its implications for asset allocation decisions. Using data from five countries — U.S., U.K., France, Germany and Japan — we find empirical evidence supporting non-linear and time-varying models for the equity risk premium. Building on this, we examine several model specifications that can account for non-linear return predictability, including Markov switching models, regression trees, random forests and neural networks. Although in-sample return regressions and portfolio allocation results support the use of non-linear predictability models, the out-of-sample evidence is notably weaker, highlighting the difficulty in exploiting non-linear predictability in real time.",

keywords = "Asset allocation, Dividend-price ratio dynamics, Dynamics and predictability of stock returns, Machine learning, Nonlinear return predictability",

author = "Fabrizio Ghezzi and Anindo Sarkar and Pedersen, {Thomas Quistgaard} and Allan Timmermann",

year = "2025",

month = mar,

doi = "10.1007/s10479-024-06332-7",

language = "English",

volume = "346",

pages = "415--445",

journal = "Annals of Operations Research",

issn = "0254-5330",

publisher = "Springer",

number = "1",

}

Optimal asset allocation and nonlinear return predictability from the dividend-price ratio. / Ghezzi, Fabrizio ; Sarkar, Anindo; Pedersen, Thomas Quistgaard et al.
In: Annals of Operations Research, Vol. 346, No. 1, 03.2025, p. 415-445.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - Optimal asset allocation and nonlinear return predictability from the dividend-price ratio

AU - Ghezzi, Fabrizio

AU - Sarkar, Anindo

AU - Pedersen, Thomas Quistgaard

AU - Timmermann, Allan

PY - 2025/3

Y1 - 2025/3

N2 - We study non-linear predictability of stock returns arising from the dividend-price ratio and its implications for asset allocation decisions. Using data from five countries — U.S., U.K., France, Germany and Japan — we find empirical evidence supporting non-linear and time-varying models for the equity risk premium. Building on this, we examine several model specifications that can account for non-linear return predictability, including Markov switching models, regression trees, random forests and neural networks. Although in-sample return regressions and portfolio allocation results support the use of non-linear predictability models, the out-of-sample evidence is notably weaker, highlighting the difficulty in exploiting non-linear predictability in real time.

AB - We study non-linear predictability of stock returns arising from the dividend-price ratio and its implications for asset allocation decisions. Using data from five countries — U.S., U.K., France, Germany and Japan — we find empirical evidence supporting non-linear and time-varying models for the equity risk premium. Building on this, we examine several model specifications that can account for non-linear return predictability, including Markov switching models, regression trees, random forests and neural networks. Although in-sample return regressions and portfolio allocation results support the use of non-linear predictability models, the out-of-sample evidence is notably weaker, highlighting the difficulty in exploiting non-linear predictability in real time.

KW - Asset allocation

KW - Dividend-price ratio dynamics

KW - Dynamics and predictability of stock returns

KW - Machine learning

KW - Nonlinear return predictability

UR - http://www.scopus.com/inward/record.url?scp=105001086702&partnerID=8YFLogxK

U2 - 10.1007/s10479-024-06332-7

DO - 10.1007/s10479-024-06332-7

M3 - Journal article

SN - 0254-5330

VL - 346

SP - 415

EP - 445

JO - Annals of Operations Research

JF - Annals of Operations Research

IS - 1

ER -

Optimal asset allocation and nonlinear return predictability from the dividend-price ratio

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this