Fulltext

Strategic asset allocation and market timing: a reinforcement learning approach

Hens, Thorsten ; Wöhrmann, Peter

In: Computational Economics, 2007, vol. 29, no. 3-4, p. 369-381

Ajouter à la liste personnelle
    Titre
    • Strategic asset allocation and market timing: a reinforcement learning approach
    Auteur
    • Hens, Thorsten. Swiss Banking Institute, University of Zürich, Plattenstrasse 32, 8032, Zürich, Switzerland
    • Wöhrmann, Peter. Department of Management Science and Engineering, Stanford University, Stanford, CA, USA
    Type de document
    • Postprint
    Langue
    • Anglais
    Publié dans
    • Computational Economics, 2007, vol. 29, no. 3-4, p. 369-381. Kluwer Academic Publishers-Plenum Publishers; http://www.springer-ny.com
    Autre version électronique
    Identifiant OAI-PMH
    • oai:doc.rero.ch:311055
    Summary
    We apply the recurrent reinforcement learning method of Moody, Wu, Liao, and Saffell (1998) in the context of the strategic assetallocation computed for sample data from US, UK, Germany, and Japan. It is found that the optimal assetallocation deviates substantially from the fixed-mix rule. The investor actively times the market and he is able to outperform it consistently over the almost two decades we analyze