Main Article Content
Following the rise and fall of cryptocurrency fees in recent years, Bitcoin has increasingly become a source of finance. There might be a need for great projections on which to base financing decisions due to its incredibly unstable nature. While the current study used system mastery to anticipate Bitcoin charges with more accuracy, few studies have examined the practicality of applying alternative modelling approaches to samples with different fact systems and dimensional capacities. We first divide the Bitcoin charge into daily and high-frequency components in order to predict it at various frequencies by employing system mastering techniques. Logistic Regression and Linear Discriminant Analysis are two statistical techniques for Bitcoin. Daily charge prediction with high-dimensional capabilities performs better than more difficult system mastering techniques with a 66 percent accuracy rate. With the best statistical techniques and system mastery algorithms with accuracy rates of 66 percent and 65.3 percent, respectively, we outperform benchmark effects for daily charge prediction. Statistics are updated from ML, models including “Random Forest, XG Boost, Quadratic Discriminant Analysis, Support Vector Machine, and Long Short-term Memory for Bitcoin 5-minute C language charge prediction, and they achieve an accuracy of 67.2 percent”. When examining the significance of pattern measurement in system mastering tactics, our research on the prediction of Bitcoin charges may be taken into account.