Valuation of Crypto Assets on Blockchain with Deep Learning Approach

Abstract

The importance of crypto-asset valuation is increasing as the ecosystem of blockchain continues to boom in recent years. We develop a deep learning framework to predict the value index of crypto assets by integrating the value variables’ information and decomposing the price into value and sentiment components. We apply the framework on ETH and AAVE, demonstrate their value indices and provide four econometric tests on the results’ quality. We show that the value index can be an effective proxy for crypto assets’ intrinsic value, and can thus provide a benchmark to the investment, consumption and financial reporting on crypto assets.

Keywords: asset valuation, block chain, crypto asset, deep learning, market sentiment

JEL Classification: G17, G12