How Numerai Works: Tournament, Staking, and the Meta-Model

Numerai is a hedge fund powered by a global tournament of data scientists. Thousands of participants download free, obfuscated financial data, build machine learning models, submit predictions, and stake NMR on their confidence. Numerai combines those predictions into a single stake-weighted "meta-model" and trades real capital on it.

The rest of this post walks through the pieces: the three tournaments, the data, the round lifecycle, scoring, staking, and how the meta-model comes together.

The Three Tournaments

Numerai runs three concurrent tournaments, each targeting different markets and data paradigms:

• Classic (Tournament 8) — Numerai provides a fully obfuscated dataset. You build ML models on their features without needing any financial domain knowledge.
• Signals (Tournament 11) — You bring your own data and generate original signals. Numerai neutralizes your signal against its existing ones to extract the unique component.
• Crypto (Tournament 12) — Targets cryptocurrency markets using Numerai's obfuscated crypto data.

The Data

In Classic, every row in the dataset represents a stock at a point in time. The data is heavily obfuscated: real financial features (P/E ratios, volume, momentum, etc.) are mathematically transformed and binned into 5 discrete values (0 through 4). Stock IDs are randomized per era so you cannot track individual stocks across time.

An era represents one weekly time slice. Training and validation data spans thousands of eras and is updated every few months. Live tournament data is released fresh each round.

You don't need to know anything about finance to compete. The obfuscation puts a strong ML practitioner on equal footing with a career quant.

Round Lifecycle

Each round follows a defined timeline from data release to payout settlement:

1. Open — New round data is released. Participants download it and run their models.
2. Close — Submission deadline. All predictions must be uploaded.
3. Stake Deadline — Last chance to adjust your NMR stake amount.
4. Scoring — Predictions are evaluated against realized stock returns over ~20 business days.
5. Resolved — Final scores are calculated and payouts settle.
6. Finalized — Round is complete and immutable.

Because the target measures roughly 20 business days of returns, each submission takes about one month to fully resolve — even though new rounds open every week (and daily rounds run in parallel). You can drill into any individual round detail to see its timeline, metric distributions, and stake breakdown.

How Scoring Works

Numerai uses four primary metrics to evaluate predictions. Each measures a different dimension of model quality:

MMC (Meta Model Contribution)

The covariance of your predictions with the target after neutralizing to the meta-model. MMC measures how much unique value your model adds beyond what the crowd already provides. It is the most important metric because it directly measures your contribution to the hedge fund. For how MMC compares to raw correlation, see MMC vs Correlation.

BMC (Bonus Meta Model Contribution)

Same concept as MMC, but neutralized against Numerai's stake-weighted benchmark models instead of the full meta-model. BMC rewards originality relative to Numerai's own baselines.

CORJ60 (Correlation Jerome 60)

Correlation of your predictions against a specific target with a 60-day lookback window and a 2-day data lag. A more direct measure of predictive accuracy.

FNCv3 (Feature Neutral Correlation v3)

Correlation with the target after neutralizing your predictions to Numerai's features. FNCv3 isolates predictive power that isn't just linear feature exposure — it rewards models that capture something the raw features don't.

The Payout Formula

Since January 2024, payouts are calculated as:

Payout Score = 0.5 x CORR + 2.0 x MMC

The 2x multiplier on MMC heavily incentivizes unique, additive predictions over simple correlation with the target.

Staking and Payouts

The staking mechanism aligns incentives: you put real money behind your predictions.

• Minimum stake: 0.01 NMR
• Maximum payout: +25% of your stake per round
• Maximum burn: -25% of your stake per round
• Payout factor: A per-round multiplier that modulates actual payouts based on tournament conditions, visible on the trends page

Payouts and burns settle after round resolution. Burned NMR is permanently destroyed — it's not redistributed to other participants.

The Meta-Model

All staked predictions are combined into a single stake-weighted meta-model:

Models with more NMR staked get proportionally more influence on the meta-model. The result is a self-filtering system: models that perform well accumulate stake and influence, while models that perform poorly burn stake and lose influence. Bad predictors get priced out over time.

Over 1,200 staked models feed the meta-model each week. The full leaderboard shows where each one ranks by reputation and returns.

Key Concepts

Obfuscated Features All data is transformed so participants cannot reverse-engineer Numerai's trading universe. This protects Numerai's IP while enabling anyone — regardless of financial background — to compete.

Target Neutralization Used in MMC and BMC scoring to strip out predictions that are already captured by the meta-model or benchmarks. Only the residual unique signal counts toward your score.

Feature Exposure Models with too much linear exposure to known features tend to perform poorly out of sample. FNCv3 specifically penalizes this. The best models capture nonlinear relationships that the raw features miss.

NMR Token

NMR (Numeraire) is an ERC-20 token on Ethereum with a hard cap of 11 million tokens. NMR cannot be minted — only burned. Tournament burns create permanent deflationary pressure. The token's primary utility is staking in the tournament — see NMR Token Economics for the full supply story.

Why It Matters

Numerai's design tackles a hard problem in quantitative finance: how do you combine work from thousands of independent researchers without them copying each other or gaming the system?

Four mechanisms do the work together: - Obfuscation prevents reverse-engineering of the trading universe - Staking forces skin in the game - MMC scoring rewards originality over conformity - The stake-weighted meta-model aggregates diverse signals into a single trading input

The output is a hedge fund whose alpha comes from the collective output of a global tournament. You can track the meta-model's inputs in real time on nmrdash — the trends page has the historical stake and payout data.