The predictive power of the Blockhain transaction networks: Towards a new generation of network science market indicators

TL;DR

This paper demonstrates that analyzing blockchain transaction network properties enhances the prediction of Ethereum's market trends beyond traditional indicators, offering a new approach in network science market analysis.

Contribution

It introduces a novel method combining blockchain network features with machine learning to improve market trend forecasting accuracy.

Findings

Full model predicts 46 more market rises than base model.

Full model predicts 19 more market falls than base model.

Network features significantly improve prediction performance.

Abstract

Currently cryptocurrencies and Decentralized Finance (DeFi), which enable financial services on public blockchains, represents a new growing trend in finance. In contrast to financial markets, ruled by traditional corporations, DeFi is completely transparent as it keeps records of all transactions that occur in the network and makes them publicly available. The availability of the data represents an opportunity to analyze and understand the market from the complexity that emerges from the interactions of the actors (users, bots and companies) operating in the embedded market. In this paper we focus on the Ethereum network and our main goal is to show that the properties of the underlying transaction network provide further and useful information to forecast the evolution of the market. We aim to separate the non redundant effects of the blockchain transaction network properties from classic technical indicators and social media trends in the future price of Ethereum. To this end, we build two machine learning models to predict the future trend of the market. The first one serves as a base model and considers a set of the most relevant features according to the current scientific literature including technical indicators and social media trends. The second model considers the features of the base model, together with the network properties computed from the transaction networks. We found that the full model outperforms the base model and can anticipate 46 more rises in the price than the base model and 19 more falls.