Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI

Markus Jaeger, Stephan Krügel, Dimitri Marinelli, Jochen Papenbrock and Peter Schwendner. Interpretable Machine Learning for Diversified Portfolio Construction. The Journal of Financial Data Science Summer 2021, jfds.2021.1.066; DOI: https://doi.org/10.3905/jfds.2021.1.066

Posted: 25 Feb 2020 Last revised: 14 Jun 2021

See all articles by Markus Jaeger

Markus Jaeger

Munich Reinsurance Company, Financial Solutions

Stephan Krügel

Munich Reinsurance Company, Financial Solutions

Dimitri Marinelli

Munich Reinsurance Company, Financial Solutions; FinNet

Jochen Papenbrock

NVIDIA GmbH

Peter Schwendner

Zurich University of Applied Sciences

Date Written: January 30, 2020

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.

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.

Keywords: Asset Allocation, explainable AI, XAI, Machine Learning, HRP, Risk Parity

JEL Classification: C15, G11, G17

Suggested Citation

Jaeger, Markus and Krügel, Stephan and Marinelli, Dimitri and Papenbrock, Jochen and Schwendner, Peter, Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI (January 30, 2020). Markus Jaeger, Stephan Krügel, Dimitri Marinelli, Jochen Papenbrock and Peter Schwendner. Interpretable Machine Learning for Diversified Portfolio Construction. The Journal of Financial Data Science Summer 2021, jfds.2021.1.066; DOI: https://doi.org/10.3905/jfds.2021.1.066, Available at SSRN: https://ssrn.com/abstract=3528616 or http://dx.doi.org/10.2139/ssrn.3528616

Markus Jaeger

Munich Reinsurance Company, Financial Solutions ( email )

Königinstr. 107
Munich, 80802
Germany

Stephan Krügel

Munich Reinsurance Company, Financial Solutions ( email )

Königinstr. 107
Munich, 80802
Germany

Dimitri Marinelli

Munich Reinsurance Company, Financial Solutions

Königinstr. 107
Munich, 80802
Germany

FinNet ( email )

Frankfurt am Main, DE

HOME PAGE: http://www.financial-networks.eu

Jochen Papenbrock

NVIDIA GmbH ( email )

Germany
+49-(0)1741435555 (Phone)

HOME PAGE: http://www.nvidia.com/en-us/industries/finance/

Peter Schwendner (Contact Author)

Zurich University of Applied Sciences ( email )

School of Management and Law
Gertrudstrasse 8
Winterthur, CH 8401
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
8,474
PlumX Metrics