FoxAlgo → Research → Academic Audit → Combining Fundamental FSCORE and Equity Short-Term Reversals

Academic audit

Failedequity XS combo

Combining Fundamental FSCORE and Equity Short-Term Reversals

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
P76
outranked ~152 of 200 baskets
Gate 3
Cost-aware net
RF -0.88
net-negative after costs
Failed
Worst 12-month leg (RF)-0.40
−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).

This is a cross-sectional equity approach that combines Piotroski's fundamental F-score (a nine-point measure of a firm's financial health) with a short-term reversal signal, buying recently weak names among fundamentally sound companies and shorting the reverse.

What we found

The apparent result was a textbook survivorship artifact. On a biased panel that quietly excludes companies which later delisted, the combination looked strongly positive; once the delisted losers are put back in, the same rules flip to a loss. In plain terms, the short-term reversal leg was largely harvesting dead names that never actually recovered. On the survivorship-free panel the risk-adjusted RF is -0.88 with a losing worst year, so we record this as a failure rather than a usable effect.

How we tested it
2005–2026 test windowmodelled liquidity-aware costssurvivorship free
  • Data: 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: Piotroski (2000) F-score x short-term reversal
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.