Publication type: Working paper – expertise – study
Title: Understanding machine learning for diversified portfolio construction by explainable AI
Authors: Jaeger, Markus
Krügel, Stephan
Marinelli, Dimitri
Papenbrock, Jochen
Schwendner, Peter
et. al: No
DOI: 10.2139/ssrn.3528616
Extent: 19
Issue Date: 2020
Publisher / Ed. Institution: SSRN
Language: English
Subjects: HRP; Machine learning; Risk parity; XAI; Asset allocation; Explainable AI
Subject (DDC): 006: Special computer methods
332.6: Investment
Abstract: In this paper, we construct a pipeline to investigate heuristic diversification strategies in asset allocation. We use machine learning concepts (“explainable AI”) to compare the robustness of different strategies and back out implicit rules for decision making. In a first step, we augment the asset universe (the empirical dataset) with a range of scenarios generated with a block bootstrap from the empirical dataset. Second, we backtest the candidate strategies over a long period of time, checking their performance variability. Third, we use XGBoost as a regression model to connect the difference between the measured performances between two strategies to a pool of statistical features of the portfolio universe tailored to the investigated strategy. Finally, we employ the concept of Shapley values to extract the relationships that the model could identify between the portfolio characteristics and the statistical properties of the asset universe. On the basis of this information, we discuss the similarity between the bootstrapped datasets characterized by their Shapley values using a network technique. We test this pipeline for studying risk-parity strategies with a volatility target, and in particular, comparing the machine learning-driven Hierarchical Risk Parity (HRP) to the classical Equal Risk Contribution (ERC) strategy. In the augmented dataset built from a multi-asset investment universe of commodities, equities and fixed income futures, we find that HRP better matches the volatility target, and shows better risk-adjusted performances. Finally, we train XGBoost to learn the difference between the realized Calmar ratios of HRP and ERC and extract explanations. The explanations provide fruitful ex-post indications of the connection between the statistical properties of the universe and the strategy performance in the training set. For example, the model confirms that features addressing the hierarchical properties of the universe are connected to the relative performance of HRP respect to ERC.
URI: https://digitalcollection.zhaw.ch/handle/11475/22054
License (according to publishing contract): Licence according to publishing contract
Departement: School of Management and Law
Organisational Unit: Institute of Wealth & Asset Management (IWA)
Appears in collections:Publikationen School of Management and Law

Files in This Item:
There are no files associated with this item.
Show full item record
Jaeger, M., Krügel, S., Marinelli, D., Papenbrock, J., & Schwendner, P. (2020). Understanding machine learning for diversified portfolio construction by explainable AI. SSRN. https://doi.org/10.2139/ssrn.3528616
Jaeger, M. et al. (2020) Understanding machine learning for diversified portfolio construction by explainable AI. SSRN. Available at: https://doi.org/10.2139/ssrn.3528616.
M. Jaeger, S. Krügel, D. Marinelli, J. Papenbrock, and P. Schwendner, “Understanding machine learning for diversified portfolio construction by explainable AI,” SSRN, 2020. doi: 10.2139/ssrn.3528616.
JAEGER, Markus, Stephan KRÜGEL, Dimitri MARINELLI, Jochen PAPENBROCK und Peter SCHWENDNER, 2020. Understanding machine learning for diversified portfolio construction by explainable AI. SSRN
Jaeger, Markus, Stephan Krügel, Dimitri Marinelli, Jochen Papenbrock, and Peter Schwendner. 2020. “Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI.” SSRN. https://doi.org/10.2139/ssrn.3528616.
Jaeger, Markus, et al. Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI. SSRN, 2020, https://doi.org/10.2139/ssrn.3528616.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.