FoxAlgo → Research → Academic Audit → Intraday ETF Momentum

Academic audit

Failedintraday ETF momentum

Intraday ETF Momentum

The three-gate gauntlet · genuine only if it clears all three and survives adversarial refutation
Gate 1
Survivorship-free
n/a
not a factor universe
Gate 2
Placebo ≥ P95
not run
Eliminated here
Gate 3
Cost-aware net
RF -1.00
net-negative after costs
Failed
Worst 12-month leg (RF)-1.00
−1.00 floor0
Every strategy here — winners included — loses in its worst 12 months. Depth is honest context, not the verdict.
Rejected at the cost gate — the net edge turns negative once modelled costs are applied.

The paper documents "market intraday momentum": the return over the first part of the trading day predicts the return in the last half hour, so a position taken late in the session follows the direction set earlier that day. This audit ports that effect to SPY (the S&P 500 ETF).

What we found

On SPY, the intraday-momentum position is net-negative once realistic trading costs are applied. It produces a risk-adjusted RF of -1.0 with zero positive years across the tested window, so the last-half-hour effect does not survive costs on this instrument. This is not a market-neutral factor-leg we can keep; the modelled frictions of repeatedly entering and exiting near the close outweigh the small directional signal. Reported failed.

How we tested it
2005–2026 test windowmodelled liquidity-aware costssurvivorship na
  • Tested on SPY (the S&P 500 ETF), intraday bars. Realistic modelled costs.
  • Placebo / robustness test: real result vs random baskets or shuffled signals (real vs the 95th percentile of random)
Source: Gao, Han, Li & Zhou (2018), "Market intraday momentum", J. Financial Economics
Read the paper ↗
← The Academic Audit — all 54 studies

Research, not investment advice. “Validated” factor-legs are market-neutral diversifying building blocks with a losing worst year — none is a standalone tradeable strategy. Metrics are cost-aware and modelled (not live fills); the 2005–2026 test window is out-of-sample versus the source paper. Dollar figures are not returns and are omitted by design.