Analysis Of Lstm-Adamax Performance In Bitcoin Price Prediction Using RSI & MACD Indicators

Abstract

One digital asset that is difficult to predict due to its extreme volatility is Bitcoin. Bitcoin's value has been predicted using various techniques, ranging from technical analysis to artificial intelligence-based models. Long Short-Term Memory (LSTM) is an artificial neural network architecture capable of recognizing patterns in historical data and is often used for time series data prediction. This study explores the application of an optimized LSTM model with the Adamax algorithm combined with the technical indicators RSI (Relative Strength Index) and MACD (Moving Average Convergence Divergence) to predict Bitcoin prices based on historical data. The LSTM-Adamax model demonstrated strong performance, achieving an RMSE of 435.9, MAE of 284.5, and R² of 0.99947, indicating high accuracy and robustness in capturing price patterns. A comparative evaluation between the model with and without these indicators revealed a slight performance improvement when the technical indicators were used. The model was successfully implemented as a web application using Streamlit, allowing users to upload Bitcoin price data, configure prediction parameters, and visualize the results in real-time. The application also communicates the predicted price movement direction (up or down) and its magnitude. In conclusion, the integration of LSTM-Adamax with RSI and MACD proved effective in predicting Bitcoin prices based on time-series data, providing reliable predictions and user-friendly implementation through a web interface.