Bitcoin has attracted a lot of attention from the media and investors, given its innovative features such as its decentralization and traceability. In some countries have accepted Bitcoin as a means of payment. Bitcoin is also commonly used as an investment asset although it is quite dangerous because the price of Bitcoin is very volatile, which means that the price can go up and down quickly in a short time. In addition, Bitcoin is also believed to be speculative, whose price goes up and down depending on people's views of the coin. This study aims to predict the price of Bitcoin using the Extreme Learning Machine (ELM) algorithm based on daily historical data by considering its speculative nature using the Google Trend Index. Based on the results of the tests carried out, the results of the Mean Absolute Percentage Error (MAPE) calculation are 3,089% using the Sigmoid activation function, 5 features, 20 neurons in the hidden layer, and using Google Trend Index with the keyword 'Bitcoin'.
Copyrights © 2022