Forecasting Bitcoin Prices: An LSTM Deep-Learning Approach Using On-Chain Data

Abstract

Over the past decade, Bitcoin’s unprecedented performance has underscored its po-sition as the premier asset class. Starting from an insignificant value and reaching an astounding high of around 65,000 U.S dollars in 2021 – all without a central con-trolling authority – Bitcoin’s trajectory is undoubtedly a historical feat. Its intangible nature, initially a subject of skepticism, has turned into an attractive quality, leading many investors to allocate a significant portion of their portfolios to Bitcoin. The traditional banking and investment sectors have also turned their attention to Bitcoin’s exponential growth. Concurrently, research on macro-economic variables and investor sentiment explaining Bitcoin’s price fluctuations has seen considerable development. However, there is a notable absence of studies leveraging On-Chain Data, information derived from transaction data in Bitcoin’s blockchain network. This paper fills this gap by using LSTM (Long Short-Term Memory), a technique widely utilized for time-series data prediction, in conjunction with On-Chain Data, to predict Bitcoin prices.