Free to preview · the playbook, published early

The 13F, six weeks early.

Autopilot lets you copy an investor after their filing is public. Prior Moves ranks the same move about six weeks sooner, for 58 US 13F filers, plus four non-US registers. Names in our top-ranked decile get bought 38.8% of the time against a 12.5% base rate on the book universe the model is scored on, and 1.72% against a 0.62% base rate on the wider board this site publishes, a 2.77x lift measured on 1.4m walk-forward rows. You place the trades at your own broker; we publish the playbook, disclosed record and predicted next move.

Build a basket Why not just copy?

Model quality, for the technically minded: the current canonical pair-weighted holdout scores 0.6762 AUC on the canonical holdout across 49 managers, 35 quarters and 124,731 held-out decisions. The top decile is bought 3.17 times as often as the 12.46% base rate. The historical median 0.659 remains in the record as a comparison point. AUC is a ranking diagnostic, not a promise of returns. How it is measured

Research, not advice. DYOR. We never execute or hold money As of Sep 2026
How it works

Three steps. The last one is yours.

§1
We read the record

Every 13F from 58 tracked investors, plus ~250 public signals: insider buys, congressional trades, activist stakes, options flow, news tone.

§2
A model per investor anticipates

Each investor gets their own model, trained on their own history, predicting their next new position, scored as a probability, published with its as-of date.

§3
You place the trades

Export a copy sheet (target weights and a dollar split) and place it at your own broker. We never execute and never hold your money.

The difference

Mirror apps copy the past. We publish the reflection early.

A 13F shows what a manager held 45+ days ago. Copy-trading products mirror that stale snapshot. We model what shows up in the next filing, about six weeks before it is public.

QUARTER ENDS 13F PUBLIC · +45 DAYS Copy-trading apps mirror the stale snapshot Prior Moves PREDICTION PUBLISHED ~6 weeks of anticipation
The dashed line is a forecast and drawn as one. Hit rate by conviction tier is published on the track record. DIAGRAM · NOT TO SCALE
Track record

489.5% cumulative return. Not yet significant.

The Top-15 basket returned 489.5% cumulatively versus 239.4% for the S&P 500 across 35 backtested quarters, with a 22.48% CAGR versus 14.99%. The 95% confidence interval includes zero and t ≈ 1.31, so this remains a directional research signal rather than proof. Excluding 2026Q1, the strategy still returned 16.35% CAGR versus 13.57% for the S&P 500.

Beat index
23 / 35 q
t-statistic
≈ 1.31
95% CI, pts/q
[−0.67, +5.86]
Quarterly win rate
65.7%
Still a backtest, not a live record. Sparser filing histories make noisier models.
Quarterly excess return vs S&P 5002017–2025 · NET OF COSTS
0 mean +0.9 2017 2025
beat the index trailed it, shown at full strength
FAQ

Fair questions.

If your question is “will this make me rich?” then no one can promise that, and we won’t.

Is this investment advice?

No. Prior Moves is a research publication. We publish model portfolios and probabilities; we never execute trades, hold money, or know your situation. What you do at your broker is your decision.

How early are the predictions?

A 13F is filed up to 45 days after quarter end. Our predictions publish about six weeks before the filing is public, each with an as-of date and the filing due date.

What happens when the model is wrong?

It often is: a P 0.68 pick should fail about a third of the time, and we grade ourselves on exactly that calibration, published per conviction tier on the track record page.

Is the edge proven?

Not yet. The Top-15 basket returned 489.5% cumulatively versus 239.4% for the S&P 500 over 35 backtested quarters. The confidence interval includes zero and t ≈ 1.31, so it is a directional signal, not proof. Excluding 2026Q1, CAGR was still 16.35% versus 13.57% for the S&P 500.

Why is it free, and how do you make money?

Every board is free to preview, five rows a table, and the track record is free in full. Subscribers pay $12 a month to see every row; your portfolio never is the business. We hold no license to your money because we never touch it.

The weekly digest

What the record says is coming next.

The predicted next buys, fresh congressional trades, and the week’s catalysts. One email a week. Honest numbers, never advice.