Research Note 03

Trend: When Published Edge Ages

Asks whether time-series momentum (well established on traditional assets by Moskowitz, Ooi & Pedersen) still holds in crypto today, or whether early favorable evidence (Liu & Tsyvinski, pre-2018 data) described a regime that has since passed. Grobys, Kolari, Sandretto, Shahzad & Äijö's 2025 study, the longest and most recent available (2016–2023, 30 large-cap coins), splits the sample by regime: strong pre-July-2020, but negative and not statistically significant in the post-July-2020 period that matters for a trader today. A single extreme outlier (Mindol, +1,400% in a day) drives much of the raw sample's insignificance; volatility-managed sizing improves the full-sample number without establishing that it survives the regime split. A broader, literature-tested 2,500-coin universe is also not a reproducible single-venue retail portfolio and posts a significantly negative spread regardless. Closed at the literature stage: no Binance replication run.

This page preserves the approved research abstract in full. The working repository contains the complete note, methodology, code, data, and references.