Cryptocurrency Portfolio Optimization by Neural Networks

TL;DR

This paper introduces a neural network-based algorithm for cryptocurrency portfolio optimization that constructs portfolios with negatively correlated assets, trained to maximize the Sharpe ratio, and demonstrates profitability across various market conditions.

Contribution

It presents a novel neural network approach with a custom loss function to optimize cryptocurrency portfolios, emphasizing negative correlation and risk minimization.

Findings

The algorithm effectively maximizes the Sharpe ratio.

Neural networks can generate profitable portfolios in different market conditions.

The approach outperforms baseline strategies in backtests.

Abstract

Many cryptocurrency brokers nowadays offer a variety of derivative assets that allow traders to perform hedging or speculation. This paper proposes an effective algorithm based on neural networks to take advantage of these investment products. The proposed algorithm constructs a portfolio that contains a pair of negatively correlated assets. A deep neural network, which outputs the allocation weight of each asset at a time interval, is trained to maximize the Sharpe ratio. A novel loss term is proposed to regulate the network's bias towards a specific asset, thus enforcing the network to learn an allocation strategy that is close to a minimum variance strategy. Extensive experiments were conducted using data collected from Binance spanning 19 months to evaluate the effectiveness of our approach. The backtest results show that the proposed algorithm can produce neural networks that are able to make profits in different market situations.