Joint work with Nusret Cakici (FU), Syed Jawad Hussain Shahzad (MBS), and Barbara Będowska-Sójka (PUEB).
Abstract: We employ a repertoire of machine learning models to investigate the cross-sectional re-turn predictability in cryptocurrency markets. While all methods generate substantial economic gains—unlike in other asset classes—the benefits from model complexity are limited. Return predictability derives mainly from a handful of simple characteristics, such as market price, past alpha, illiquidity, and momentum. Contrary to the stock market, abnormal returns in cryptocurrencies originate from the long leg of the trade and persist over time. Furthermore, despite high portfolio turnover, most machine learning strategies remain profitable after trading costs. However, alphas are concentrated in hard-to-trade assets and critically depend on harvesting extreme returns on small, illiquid, and volatile coins.
Presentations: FFEA Ghent 2023, 43rd EBES, John von Neumann University, Prince Sultan University,
Online application visualizes the performance of the ML strategies tested in the paper.