In his paper, set of Bitcoin price data is analyzed by using three types of machine learning techniques: Artificial Neural Network, Support Vector Machine and Random Forest to predict Bitcoin price trend in 1-day, 3-day and 5-day using 10 technical indicators as input, based on time series of open price, close price, high price and low price of Bitcoin. The results show that the support vector machine model gave the highest accuracy. The accuracy of 63.70%, 65.07% and 65.75%, respectively, are higher than the other previous research.