A Review on Machine Learning Models for Forecasting Crypto Prices

Cryptocurrencies, since the launch of Bitcoin in 2008, have transformed from niche digital assets into significant financial instruments. Over time, the market has expanded to thousands of cryptocurrencies with varied applications, from digital currencies to platforms for decentralized finance (DeFi), non-fungible tokens (NFTs), and smart contracts. Market capitalization—calculated by multiplying a cryptocurrency’s current price by its circulating supply—serves as an indicator of a coin’s prominence and perceived value within the market. Forecasting the price of cryptocurrencies has remained a serious challenge due to the inherent volatility of the prices. This paper presents a review on contemporary data driven approaches for crypto currency forecasting highlighting the salient attributes. Moreover, the identified non-trivial research gap in the existing approaches has been used as an underpinning for subsequent direction of research in the domain. The paper culminates with the performance metrics and concluding remarks.