The Bitcoin strategy uses machine learning to predict returns, rebalancing daily with a mean-variance framework, leveraging up to 2x long and limiting short exposure to 100%, optimizing risk and returns.

I. STRATEGY IN A NUTSHELL

This strategy trades Bitcoin using predictive models (SGD + XGBoost) on features like momentum, sentiment, and network value-to-transaction ratios. Daily portfolio allocation between Bitcoin and cash follows a mean-variance framework, with asymmetric leverage: up to 2× long and 1× short.

II. ECONOMIC RATIONALE

Cryptocurrency markets are driven by behavioral risk premia—momentum and sentiment. The strategy exploits these dynamics via trend-following, anticipating selloffs and capitalizing on speculative price movements, aligning with the unique behavior of crypto investors.

III. SOURCE PAPER

Boosting Cryptocurrency Return Prediction [Click to Open PDF]

Ilias Filippou, Washington University in St. Louis; David Rapach, Federal Reserve Bank of Atlanta; Christoffer Thimsen, Aarhus University

<Abstract>

We investigate the out-of-sample predictability of daily cryptocurrency returns using modern machine-learning methods. We consider a large number of cryptocurrencies (41) and a rich set of predictors relating to network value and activity, momentum, technical signals, and online activity. We find that return predictability is an important feature of the cryptocurrency market: machine-learning methods significantly improve the statistical accuracy of cryptocurrency return forecasts and provide substantial economic value to investors. Predictors relating to momentum, size, and value stand out as important determinants of future cryptocurrency returns. Nonlinearities also play a significant role in improving cryptocurrency return predictability.

IV. BACKTEST PERFORMANCE

Annualised Return21.89%
Volatility9.42%
BetaN/A
Sharpe Ratio2.06
Sortino RatioN/A
Maximum Drawdown-7.53%
Win RateN/A

Leave a Reply

Discover more from Quant Buffet

Subscribe now to keep reading and get access to the full archive.

Continue reading