Anmerkungen:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments September 19, 2022 erstellt
Beschreibung:
We systematically re-examine the efficacy of trend-based technical indicators in predicting cryptocurrency market returns at daily, weekly, and monthly horizons. It shows that the price-based signals are more effective than the volume-based signals in the short horizon (daily and weekly), while the volume-based signals are more powerful in the long horizon (monthly). We also document that machine learning techniques can significantly improve the performance of technical indicators both in and out of sample at all horizons. Further analysis reveals that leading cryptos are more predictable by technical analysis, and technical indicators based on different information respond differently to the COVID-19 outbreak