Diverging Roads: Theory-Based vs. Machine Learning-Implied Stock Risk Premia.

We compare the performance of theory-based and machine learning (ML) methods for quantifying equity risk premia and assess hybrid strategies that combine the two very different philosophies. The theory-based approach offers advantages at a one-month investment horizon, in particular, if daily freque...

Full description

Bibliographic Details
Published in:Journal of Financial Econometrics Vol. 23; no. 2; pp. 1 - 56
Main Authors: Grammig, Joachim, Hanenberg, Constantin, Schlag, Christian, Sönksen, Jantje
Format: Article
Published: Oxford University Press / USA 2025
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=184193010&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 184193010
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        14798409
        T2Y
      jtl: Journal of Financial Econometrics
      issn: 14798409
      maglogo: N
    pubinfo:
      dt: 2025
      vid: 23
      iid: 2
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        184193010
        10.1093/jjfinec/nbaf005
      ppf: 1
      ppct: 55
      formats:
      tig:
        atl: Diverging Roads: Theory-Based vs. Machine Learning-Implied Stock Risk Premia.
      aug:
        au:
          Grammig, Joachim
          Hanenberg, Constantin
          Schlag, Christian
          Sönksen, Jantje
        affil:
          Department of Statistics, Econometrics and Empirical Economics, University of Tübingen, Mohlstrasse 36, Tübingen, 72074, Germany
          Centre for Financial Research (CFR), Albertus-Magnus-Platz, Cologne, 50923, Germany
          House of Finance, Goethe University Frankfurt, Theodor-W.-Adorno-Platz 1, Frankfurt/Main, 60629, Germany
          Leibniz Institute for Financial Research SAFE, Theodor-W.-Adorno-Platz 3, Frankfurt/Main, 60323, Germany
          Institute for Econometrics and Data Science, Leibniz University Hannover, Königsworther Platz 1, Hannover, 30167, Germany
      su:
        Risk premiums
        Machine learning
        Random forest algorithms
        Stock options
        Approximation error
      sug:
        subj:
          Investment Banking and Securities Dealing
          Risk premiums
          Machine learning
          Random forest algorithms
          Stock options
          Approximation error
      keyword:
        C53
        C58
        G12
        G17
        machine learning
        option prices
        stock risk premia
        C53
        C58
        G12
        G17
        machine learning
        option prices
        stock risk premia
      ab: We compare the performance of theory-based and machine learning (ML) methods for quantifying equity risk premia and assess hybrid strategies that combine the two very different philosophies. The theory-based approach offers advantages at a one-month investment horizon, in particular, if daily frequency risk premium estimates (RPE) are needed. At the one-year horizon, ML has an edge, especially using theory-based RPE as additional feature variables. For a hybrid strategy called Theory with ML Assistance , we employ ML to account for the approximation errors of the theory-based approach. Employing random forests or an ensemble of ML models for theory support yields promising results.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N