Using Regression and Algorithms in Artificial Intelligence to Predict the Price of Bitcoin

Abstract

AbstractCryptocurrency is a topic that is no longer strange in the investment world. Bitcoin is considered a very famous cryptocurrency and has a large amount of investment across the globe. Therefore, in recent years, the Bitcoin investment field has been attracting much research to help investors in this field maximize profits. In this study, using regression and algorithms in artificial intelligence such as K-Nearest Neighbors (K-NN), Neural Network (NN), Decision Tree (DT), Support Vector Machines (SVM), Random Forest (RF), and Linear Regression (LR) to predict the opening price of Bitcoin. We are using the hybrid model of the LR algorithm with K-NN, NN, DT, SVM, and RF algorithms to improve Bitcoin price prediction performance. The study results show that most algorithms predict well, and the hybrid model has better prediction results. This prediction result shows that the hybrid model has the potential to be applied in practice to improve the accuracy of Bitcoin opening price prediction.KeywordsCryptocurrency predictionBitcoin predictionMachine learningHybrid model