Enhancing Cryptocurrency Prediction: A Fusion of Machine Learning and Neutrosophic Programming

Fluctuations in cryptocurrency markets present a significant problem to the accuracy of forecasting trends and prices in this field. This paper proposes a new method of improving cryptocurrency forecasting by applying machine learning algorithms to a hybrid model. The framework integrates, a neural network model, with auto regressive integrated moving average (ARIMA) and trigonometric, Box-Cox, ARMA, Trend, Seasonal (TBATS) to capture the intricate relationship and dynamics in the data. Because most aspects affecting the cryptocurrency’s price are uncertain, we propose that fuzzy parameters be used to reflect this uncertainty in the market. Furthermore, we apply neutrosophic programming to optimize predictions where the indeterminacy of the data is considered. The hybrid model thus incorporates short-term market volatility and long-term market trends, making the model rigid and accurate. Here, we compare this approach’s performance with other forecasting models using actual cryptocurrency data. The results indicate that the hybrid model developed achieves better predictive accuracy and is more flexible than the conventional models. To sum up, this research offers significant knowledge of applying the newest machine learning methods to enhance cryptocurrency prediction and improve its efficiency for investors, traders, and financial institutions.