Practical Forecasting of Cryptocoins Timeseries using Correlation Patterns

TL;DR

The paper addresses the volatile and interdependent nature of cryptocurrency prices by mapping cross-coin correlations and testing Granger-causality to identify predictor altcoins for BTC and ETH. It combines correlation analysis across multiple time scales with causal testing (Toda–Yamamoto) and evaluates time-series forecasting using gradient-boosting machines and recurrent neural networks, finding GBMs generally provide more accurate forecasts. Key contributions include a large-scale correlation study, empirical causality results showing altcoins as predictive signals, and a comparative forecasting evaluation with reproducible datasets and code. The work offers practical insights for improving crypto price forecasting and risk assessment, with implications for traders and researchers and strong emphasis on open science.

Abstract

Cryptocoins (i.e., Bitcoin, Ether, Litecoin) are tradable digital assets. Ownerships of cryptocoins are registered on distributed ledgers (i.e., blockchains). Secure encryption techniques guarantee the security of the transactions (transfers of coins among owners), registered into the ledger. Cryptocoins are exchanged for specific trading prices. The extreme volatility of such trading prices across all different sets of crypto-assets remains undisputed. However, the relations between the trading prices across different cryptocoins remains largely unexplored. Major coin exchanges indicate trend correlation to advise for sells or buys. However, price correlations remain largely unexplored. We shed some light on the trend correlations across a large variety of cryptocoins, by investigating their coin/price correlation trends over the past two years. We study the causality between the trends, and exploit the derived correlations to understand the accuracy of state-of-the-art forecasting techniques for time series modeling (e.g., GBMs, LSTM and GRU) of correlated cryptocoins. Our evaluation shows (i) strong correlation patterns between the most traded coins (e.g., Bitcoin and Ether) and other types of cryptocurrencies, and (ii) state-of-the-art time series forecasting algorithms can be used to forecast cryptocoins price trends. We released datasets and code to reproduce our analysis to the research community.

Figures (8)

• Figure 1: Top-5 most-traded cryptocoins from March 1st, 2020 until March, 3rd, 2023. Dataset from Binance binance.
• Figure 2: Ensemble learning techniques: bagging and boosting.
• Figure 3: Deep Learning approaches to time series forecasting: "vanilla" RNN, LSTM and GRU.
• Figure 4: Closing prices of BTC/ETH with validation/test split.
• Figure 5: Correlogram between the average OHLC price and volume of 60 alt-coins and BTC (top) and ETH (bottom). Data from CoinMarketCap. Bold: coins used in §\ref{['sec:causality']}.