Bitcoin Price Prediction Based on Multiple Machine Learning Algorithms

Abstract

In this paper, we performed bitcoin price prediction based on bitcoin price dataset using Support Vector Machine model, Random Forest model, Neural Network model, XGBoost model and LightGBM model and evaluated the performance of these models. We divided the Bitcoin price dataset into training and test sets in a ratio of 7:3, where 70 were used as the training set and 30 as the test set. The models were trained with the training set and tested with the test set using the stock price change (yield) as the target variable and other variables as input variables. By comparing the MSE, RMSE, MAE, MAPE and R of the different models were evaluated and it was found that XGBoost has the best performance and the best prediction. The performance of the other four models ranged from good to poor, including LightGBM, Random Forest, Support Vector Machine and Neural Network. Among them, the neural network, whose MSE is tens of times higher than the other four models, performs the worst. The research results in this paper can provide reference value for future Bitcoin price prediction, and also provide some reference for choosing appropriate machine learning models.