Sparse autoencoders improve diversification in crypto portfolios
Sparse Autoencoders as Implicit Diversification Regularisers for Cross-Sectional Cryptocurrency Returns
Machine Learning
Summary
Building investment portfolios often involves finding factors that explain asset returns, but neural network–based factors can be hard to understand and unstable. The authors look at a specific neural network technique called sparse autoencoders to represent cryptocurrency returns with only a few active features. They find that portfolios created this way tend to have lower volatility because the assets selected are less correlated. However, these sparse features are not consistent across different training attempts, and the method doesn’t beat simpler investment strategies on risk-adjusted returns.
What this means in practice
- •For portfolio managers: Create portfolios with lower volatility by using sparse autoencoders to select less correlated cryptocurrency assets.
- •For quantitative traders: Improve risk management by incorporating sparse coding techniques to reduce asset correlations in diversified crypto portfolios.
Authors
Weijia Han, Lisha Qu
Abstract
Factor models are central to asset pricing and portfolio construction, but neural factors are often difficult to interpret, and their effect on portfolio risk is unclear. A sparse autoencoder (SAE) may address both concerns by describing daily returns across many assets with only a few active features. We ask whether this sparse representation produces stable financial factors and better-diversified portfolios. We study cryptocurrency returns, use equities as a secondary test, and compare the SAE with common benchmarks in a time-ordered evaluation. We find consistently lower volatility in SAE portfolios and link this result to lower correlations among the selected assets. However, the SAE does not outperform a simple contrarian strategy on risk-adjusted return, and its factor identities are not stable across training runs. Our contribution is to show that sparse coding can support portfolio diversification, while clearly separating this risk effect from claims about alpha or stable factor identities.