Time Series Analysis For Bitcoin Price Prediction Using Prophet

This study focuses on time series analysis for predicting Bitcoin prices using various methodologies, including Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), Auto Regressive Integrated Moving Average (ARIMA), and Facebook's Prophet. We utilize a dataset consisting of timestamps and closing prices to train and evaluate the performance of these models. The objective is to identify the most effective forecasting technique for Bitcoin price movements, addressing the inherent volatility of cryptocurrency markets. By leveraging historical price data, we aim to enhance prediction accuracy, contributing to more informed trading decisions. Our findings will provide valuable insights into the applicability of different predictive models in the context of cryptocurrency, ultimately aiming to assist investors in navigating the complexities of Bitcoin trading. The results underscore the strengths and weaknesses of each method, paving the way for future research in financial time series analysis.

Keywords: RNN, LSTM, ARIMA and Prophet, Kaggle dataset.