A Trend Factor for the Cross-Section of Cryptocurrency Returns

Authors:

Abstract
We propose CTREND, a new trend factor for cryptocurrency returns, which aggregates price and volume information across various horizons. Using data on more than 3,000 coins, we employ machine learning methods to exploit information from various technical indicators. The resulting signal reliably predicts the cross-section of cryptocurrency returns. The effect cannot be subsumed by known factors and remains remarkably robust, holding for various subperiods, market states, and alternative research designs. Furthermore, it survives the impact of transaction costs and persists in large and liquid coins, paving the way for an effective trading strategy. Notably, an asset pricing model that incorporates CTREND outperforms competing factor models, offering a superior explanation of cryptocurrency returns.

This publication has 110 references indexed in Scilit: