Prediksi Harga Bitcoin Menggunakan Algoritma Long Short Term Memory (LSTM)

Abstract

Cryptocurrency is a digital currency made from sequence code or called blockchain, one of the cryptocurrencies is bitcoin. Prediction is a process that projects or imagines what might happen in the future based on data in the past or factors that influence the current situation. Bitcoin price prediction uses a deep learning approach with the Long Short Term Memory method. Long Short-Term Memory is a type of model from the Recurrent Neural Network (RNN) algorithm, a method designed to process data and can overcome the problem of price movements that have long-term dependencies that cannot be handled by traditional RNN models, the LSTM model has the ability “Remembers” information over long periods of time, so as to recognize patterns and trends. In this study, the prediction period used a dataset from 12 December 2020 to 14 April 2024. The evaluation results for the RMSE method for train data were 17318.40 and for test data were 27921.84 and for the MAPE method for train data it was 3.24% and for test data it was 3.24%. 5.36%. This shows that the RMSE and MAPE values in the data train are relatively small because they are vulnerable to the bitcoin price being too wide.