Daily Cryptocurrency Returns Forecasting and Trading via Machine Learning

Abstract

We execute a comparative analysis of machine learning models for the time-series forecasting of the sign of next-day cryptocurrency returns. We begin by compiling a proprietary dataset that encompasses a wide array of potential cryptocurrency valuation factors (price trends, liquidity, volatility, network, production, investor attention), subsequently identifying and evaluating the most significant factors. We apply eight machine learning models to the dataset, utilizing them as classifiers to predict the sign of next day price returns for the three largest cryptocurrencies by market capitalization: bitcoin, ethereum, and ripple. We show that the most significant valuation factors for cryptocurrency returns are price trend variables, seven and thirty-day reversal, to be specific. We conclude that support vector machines result in the most accurate classifications for all three cryptocurrencies. Additionally, we find that boosted models like AdaBoost and XGBoost have the poorest classification accuracy. At length, we construct a probability-based trading strategy that secures either a daily long or short position on one of the three examined cryptocurrencies. Ultimately, the strategy yields a Sharpe of 2.8 and a cumulative log return of 3.72. On average, the strategy’s log returns outperformed standalone investments in all three cryptocurrencies by a factor of 5.64, and Sharpe ratios more than threefold.

Intensification Dimension of Prices Cryptocurrency with Hamiltonian Quantum Mechanics

“…The indications in Table 4 in the price momentum indicator are consistent with the hypothesis statement, like positive but not significant or departing from the arguments of the [30] and [31] panels. However, it is significant and positive in Table 5 with cryptocurrency BNB, which has become an asset that the spread of momentum flows cannot be determined.…”

“…The formulation of results (11) will follow the random variable from CCPI as the existence of the possibility of fluctuations is appropriate and correlated with price indicators [33,31]. The price fluctuation of cryptocurrencies (Table 2) is generally higher than the average price value.…”

“…The financial particle will, however, change rapidly and in discrete leaps since the stimulus flow is non-directional [30]. As a result, price momentum and cryptocurrency returns are significantly correlated [31].…”

“…BTC is becoming a significant asset price and has some speculative free pricing options [29]. While the price of cryptocurrency BNB does not derive from all available prices and does not fluctuate from discrete returns, the issue of BNB securities is contradictory [31,30] because the risk with a free price rate approaches that of the BNB asset price, allowing it to become a price mover.…”

“…5 depicts the issue of the intensification of crypto assets (shown on the left), which is exacerbated by the fact that the moment of fluctuation is impacted by a range of bound attitudes from various sectors of crypto trading activity [42]. Compared to three other cryptocurrencies, BNB has varied returns that are not restricted by price momentum [31]. However, the panel of discrete results (right figure) is only partly connected [30].…”