FoxAlgo → Research → Academic Audit → Residual Momentum Factor

Academic audit

Failedequity XS momentum

Residual Momentum Factor

The three-gate gauntlet · genuine only if it clears all three and survives adversarial refutation
Gate 1
Survivorship-free
free
clean panel
Eliminated here
Gate 2
Placebo ≥ P95
P0
outranked ~0 of 200 baskets
Gate 3
Cost-aware net
RF -0.82
net-negative after costs
Failed
Worst 12-month leg (RF)-0.93
−1.00 floor0
Every strategy here — winners included — loses in its worst 12 months. Depth is honest context, not the verdict.
Rejected at the luck gate — its net ranked no better than random baskets (below the P95 skill line).

Residual momentum ranks stocks on their past returns after stripping out the part explained by the Fama-French three-factor model, then goes long recent winners and short recent losers on that residual signal. The claim is that momentum measured on idiosyncratic (residual) returns is cleaner than plain price momentum.

What we found

In our survivorship-free test the factor failed: it lands at the 0th placebo percentile, meaning random baskets of the same shape did better across the board, and its risk-adjusted RF is negative. The residualization removes exactly the component that carried plain cross-sectional momentum, so what remains does not survive realistic costs. This is a failed leg, not a diversifying building block.

How we tested it
2005–2026 test windowmodelled liquidity-aware costssurvivorship free
  • Tested on a survivorship-free 1077-name US common-stock panel, 2005-2026. Realistic modelled costs.
  • Placebo / robustness test: real result vs random baskets or shuffled signals (real vs the 95th percentile of random)
Source: Blitz, Huij & Martens (2011), "Residual Momentum", J. Empirical Finance
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.