Deeply Equal-Weighted Subset Portfolios

TL;DR

This paper introduces Deeply Equal-Weighted Subset Portfolios (DEWSP), a data-driven approach using deep learning to select and equally weight top assets, improving risk-adjusted returns over traditional methods.

Contribution

The paper proposes a novel portfolio model that combines deep learning-based asset ranking with equal weighting, reducing sensitivity to estimation errors and enhancing practical applicability.

Findings

DEWSP improves Sharpe ratio by up to 5.15% over benchmarks.

DEWSP is purely data-driven and does not rely on expert judgment.

Adjusting N allows targeting specific risk-return profiles.

Abstract

The high sensitivity of optimized portfolios to estimation errors has prevented their practical application. To mitigate this sensitivity, we propose a new portfolio model called a Deeply Equal-Weighted Subset Portfolio (DEWSP). DEWSP is a subset of top-N ranked assets in an asset universe, the members of which are selected based on the predicted returns from deep learning algorithms and are equally weighted. Herein, we evaluate the performance of DEWSPs of different sizes N in comparison with the performance of other types of portfolios such as optimized portfolios and historically equal-weighed subset portfolios (HEWSPs), which are subsets of top-N ranked assets based on the historical mean returns. We found the following advantages of DEWSPs: First, DEWSPs provides an improvement rate of 0.24% to 5.15% in terms of monthly Sharpe ratio compared to the benchmark, HEWSPs. In addition, DEWSPs are built using a purely data-driven approach rather than relying on the efforts of experts. DEWSPs can also target the relative risk and return to the baseline of the EWP of an asset universe by adjusting the size N. Finally, the DEWSP allocation mechanism is transparent and intuitive. These advantages make DEWSP competitive in practice.