Insider Signal Scorecard — July 2026
Don’t outsource your judgment · monthly scorecard
Did our insider signals beat the market? Every month we grade our own published pipeline in public — every bucket, including the ones that underperform, with the statistics next to the returns. This is the July 2026 report.
The headline
Across 1242 matured opportunistic buys, the average edge over the S&P 500 (63 trading days) is 0.0%. Is that edge real, statistically? not yet proven — the sample is still growing (t-stat -0.04).
Every bucket, no cherry-picking
| Signal bucket | Events | Raw +63d | ★ vs S&P (63d) | Hit rate |
|---|---|---|---|---|
| All opportunistic buys (the baseline) | 1242 | +5.7% | 0.0% | 57% |
| ★ High conviction (score 70+) | 109 | +9.1% | +4.6% | 63% |
| Low conviction (<45) — our internal control | 425 | +2.9% | -1.0% | 56% |
| Big stake increase (≥30% / first buy) | 316 | +8.3% | +4.1% | 62% |
| CFO / COO buys | 70 | +6.8% | +2.7% | 64% |
| Cluster buys (≥3 insiders) | 276 | +3.7% | -0.5% | 56% |
| Low-density (rare) buyers | 447 | +9.5% | +1.0% | 55% |
| $100K+ buys | 795 | +6.5% | +0.1% | 56% |
| Offensive (quiet accumulation) | 216 | +1.0% | -2.8% | 44% |
| Defensive (support buying) | 257 | +5.9% | +1.3% | 57% |
Raw returns are greyed because they mostly reflect the market itself; the ★ column strips the S&P out — that’s the edge, if any. Rows under 25 events are faded: too few to mean anything. The “low conviction” row is our own control group — if it ever beats our high-conviction picks over a real sample, our scoring isn’t working, and this report will say so.
Check our work
The signal ledger lists every high-conviction signal ever logged — timestamped before the outcome, graded as it matures, never deleted. The live feed and full methodology (Cohen–Malloy–Pomorski, Journal of Finance) are on the Insider Signals page.
All figures are hypothetical event-study returns computed from public SEC filings and market prices — no trading costs, taxes, or slippage. Past performance, real or hypothetical, does not predict future results. Educational, not investment advice. See Disclosures.