Publikationstyp: | Beitrag in wissenschaftlicher Zeitschrift |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Interpretable machine learning for diversified portfolio construction |
Autor/-in: | Jaeger, Markus Krügel, Stephan Marinelli, Dimitri Papenbrock, Jochen Schwendner, Peter |
et. al: | No |
DOI: | 10.3905/jfds.2021.1.066 |
Erschienen in: | The Journal of Financial Data Science |
Band(Heft): | 3 |
Heft: | 3 |
Seite(n): | 31 |
Seiten bis: | 51 |
Erscheinungsdatum: | 2021 |
Verlag / Hrsg. Institution: | Portfolio Management Research |
ISSN: | 2640-3943 2640-3951 |
Sprache: | Englisch |
Schlagwörter: | Big data; Machine learning; Performance measurement; Statistical method |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren 332.6: Investition |
Zusammenfassung: | In this article, the authors construct a pipeline to benchmark hierarchical risk parity (HRP) relative to equal risk contribution (ERC) as examples of diversification strategies allocating to liquid multi-asset futures markets with dynamic leverage (volatility target). The authors use interpretable machine learning concepts (explainable AI) to compare the robustness of the strategies and to back out implicit rules for decision-making. The empirical dataset consists of 17 equity index, government bond, and commodity futures markets across 20 years. The two strategies are back tested for the empirical dataset and for about 100,000 bootstrapped datasets. XGBoost is used to regress the Calmar ratio spread between the two strategies against features of the bootstrapped datasets. Compared to ERC, HRP shows higher Calmar ratios and better matches the volatility target. Using Shapley values, the Calmar ratio spread can be attributed especially to univariate drawdown measures of the asset classes. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/23004 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
Departement: | School of Management and Law |
Organisationseinheit: | Institut für Wealth & Asset Management (IWA) |
Enthalten in den Sammlungen: | Publikationen School of Management and Law |
Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige
Jaeger, M., Krügel, S., Marinelli, D., Papenbrock, J., & Schwendner, P. (2021). Interpretable machine learning for diversified portfolio construction. The Journal of Financial Data Science, 3(3), 31–51. https://doi.org/10.3905/jfds.2021.1.066
Jaeger, M. et al. (2021) ‘Interpretable machine learning for diversified portfolio construction’, The Journal of Financial Data Science, 3(3), pp. 31–51. Available at: https://doi.org/10.3905/jfds.2021.1.066.
M. Jaeger, S. Krügel, D. Marinelli, J. Papenbrock, and P. Schwendner, “Interpretable machine learning for diversified portfolio construction,” The Journal of Financial Data Science, vol. 3, no. 3, pp. 31–51, 2021, doi: 10.3905/jfds.2021.1.066.
JAEGER, Markus, Stephan KRÜGEL, Dimitri MARINELLI, Jochen PAPENBROCK und Peter SCHWENDNER, 2021. Interpretable machine learning for diversified portfolio construction. The Journal of Financial Data Science. 2021. Bd. 3, Nr. 3, S. 31–51. DOI 10.3905/jfds.2021.1.066
Jaeger, Markus, Stephan Krügel, Dimitri Marinelli, Jochen Papenbrock, and Peter Schwendner. 2021. “Interpretable Machine Learning for Diversified Portfolio Construction.” The Journal of Financial Data Science 3 (3): 31–51. https://doi.org/10.3905/jfds.2021.1.066.
Jaeger, Markus, et al. “Interpretable Machine Learning for Diversified Portfolio Construction.” The Journal of Financial Data Science, vol. 3, no. 3, 2021, pp. 31–51, https://doi.org/10.3905/jfds.2021.1.066.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.