In this article, we delve into the challenging task of accurately forecasting financial returns, specifically focusing on cryptocurrency returns. Cryptocurrency markets are known for their chaotic and complex nature, making the prediction process even more arduous. However, using a novel prediction algorithm rooted in the Hawkes model and limit order book (LOB) data, we present a precise forecast of return signs. By leveraging predictions of future financial interactions and capitalizing on the non-uniformly sampled structure of the original time series, our approach outperforms benchmark models in both prediction accuracy and cumulative profit in a trading environment. To prove the efficacy of our approach, we conduct Monte Carlo simulations across 50 scenarios utilizing LOB measurements from a centralized cryptocurrency exchange involving the stablecoin Tether and the U.S. dollar.
Abstract:Accurately forecasting the direction of financial returns poses a formidable challenge, given the inherent unpredictability of financial time series. The task becomes even more arduous when applied to cryptocurrency returns, given the chaotic and intricately complex nature of crypto markets. In this study, we present a novel prediction algorithm using limit order book (LOB) data rooted in the Hawkes model, a category of point processes. Coupled with a continuous output error (COE) model, our approach offers a precise forecast of return signs by leveraging predictions of future financial interactions. Capitalizing on the non-uniformly sampled structure of the original time series, our strategy surpasses benchmark models in both prediction accuracy and cumulative profit when implemented in a trading environment. The efficacy of our approach is validated through Monte Carlo simulations across 50 scenarios. The research draws on LOB measurements from a centralized cryptocurrency exchange where the stablecoin Tether is exchanged against the U.S. dollar.