Chat Forum Tournament

Numerai has gathered the best data scientists in the world and let them build machine learning models on the highest quality stock market data.

The result is a next-generation hedge fund which is outperforming market neutral indexes and traditional quant funds.

Numerai has gathered the best data scientists in the world and let them build machine learning models on the highest quality stock market data.

The result is a next-generation hedge fund which is outperforming market neutral indexes and traditional quant funds.




Aurum Quant Equity Market Neutral Index

Get in touch

If you're interested, schedule a call or mail us.

Receive email updates

Subscribe to our regular performance and news emails:

We'll never share your email with anyone else.

Numerai is stock selection alpha.

80% of our returns come from non-factor exposure which means our fund can work well when factors stop working. Many market neutral funds like AQR run factor exposure risks which can perform poorly during times of market stress like in 2020.

article Take a deep dive into Numerai's performance

Investment Process

1 Regularized Data

Numerai researches and combines a large number of data sources together and transforms the data into regularized features and targets to create a pure dataset for Numerai's data science community.

2 Modeling

Datasets are made available to our community of data scientists who compete to create the best predictive models in our data science tournament.

3 Stakes

Data scientists stake their best models with our cryptocurrency, NMR. Good models are rewarded with more NMR. Bad models have their stakes burned.

4 Stake-Weighted Meta Model Signal

Numerai creates the Stake-Weighted Meta Model by combining the latest predictions from the tournaments and outputs a signal for each stock in our investable universe.

5 Portfolio Construction

Convex optimization turns Meta Model signal into a portfolio by constraining risk factors such as country, sector and market risk.

6 Portfolio Returns

Numerai's returns are uncorrelated with the market and uncorrelated with traditional quant funds creating a differentiated and diversifying asset for institutional allocators.

Skin in the game incentivizes the crowd.

Numerai uses cryptocurrency staking to incentivize our global network of data scientists to submit the best possible machine learning models which power our global equity hedge fund. We never trade crypto. But we have created an institutional grade market neutral hedge fund using crypto incentives.


staked AI models power Numerai


at stake


Richard Craib

Founder and Chief Executive Officer

Machine Learning Quantitative Investor: Prudential Asset Management

Cornell University: Pure Math

Rich Allen

Managing Director

Chief Operating Officer: Mission Value Partners

Managing Director, Global Head of Sales: Tora Trading Services

Rui Tang

Director of Portfolio Management

Portfolio Manager: MacKay Shields

Harvard University: Statistics

Dan Spier

Chief Operating Officer

Head of Portfolio Trading: Aperio Group

Partner: Standard Pacific Capital

Learn more about the Meta Model

Frequently Asked Questions

What is Numerai?

Numerai is a quant hedge fund built on thousands of crowdsourced machine learning models.

What's in the Numerai dataset?

The Numerai dataset consists of standard financial market data for a universe of roughly 5,000 global equities. We assemble it from several market data providers and consistently research both traditional and unique features in data that's available over a 10-20 year timeframe.

Why give it away for free?

Numerai gives away data so that users around the world have free, hedge-fund quality data to build their machine learning models -- data they would otherwise not have access to. From inception, Numerai has believed that open participation, in the form of readily available data, is a core component in crowdsourcing solutions to significant data science problems.

Why is the data obfuscated for the tournament participants?

Finding a way to share data without revealing it, a solution that allows us to freely distribute a high-quality set of financial data, was also an early, core innovation that Numerai built. We needed a way to secure the value of the data set while simultaneously retaining its unique features for the purpose of building predictive models with machine learning.

How has the data set evolved over time?

Numerai data has significantly expanded over several iterations: The original data set contained just 40 individual features and a single target variable. In subsequent releases, the feature count expanded to 310, and then to over 1,000 most recently with our Fall 2021 release. More data means better model performance.

Why and how do users stake on the models that they submit?

The ability for Numerai tournament participants to stake on the predictive accuracy of their models is another core innovation we designed. "Skin in the game" both rewards accurate predictions and penalizes inaccurate submissions. Effectively, it is a way to align incentives and engender trust between Numerai and those submitting their models.

Staking is done with NMR, a crypto-token Numerai launched in 2017. NMR trades freely on several of the major crypto exchanges (Coinbase, Binance, etc.) and its utility is solely to stake on models in the Numerai tournament. Based on a scoring metric, users receive a fractional payout on their stake for performant models, with a portion of the stake being burned (destroyed) for poorly performing models. Stake payouts and burns occur on a blockchain with no direct financial benefit accruing to Numerai.

What are the basic guidelines of the tournament?

The Numerai data tournament occurs weekly; Participants must submit ranked signals for all ~5,000 global equities in the Numerai data set, forecasting performance over a 20 day (four week) period. Only individual stock predictions, and not any actual models nor code are submitted.

While staking is not required, only staked submissions will be incorporated into Numerai's meta model which ultimately manages the trading for and the portfolios in the Numerai hedge fund.

As of April 2022, approximately 4,500 staked models have been submitted for the most recent data tournament, with a staked amount totaling $20 million.

What is the Numerai Meta Model?

The Numerai Meta Model is an ensemble of the individual models that are submitted as part of the Numerai data tournament. Crowdsourcing predictive models and then combining those signals at scale is another unique innovation that Numerai has developed.

The concept of a performant meta model is predicated on the idea that a broad and diverse selection of uncorrelated models will more accurately predict the outcome of a complex data science problem. Particularly, in the case of predicting financial markets where high accuracy and low variance (a high Sharpe ratio) matter more, this kind of ensembling exercise is doubly helpful.

Five and half years of iterating on this concept of meta model supremacy (better than simple regression, better than an individual handful of correlated machine learning models) has proven out. Numerai's ability to design the right kind of targets in our data set and our ability to neutralize the impact of traditional risk factors have also contributed to the growth in performance of the Numerai hedge fund over the past several years.

What are the characteristics of the Numerai hedge fund portfolios?

The Numerai hedge fund consists of equally weighted long and short portfolios with approximately 500 individual equities in each portfolio. The beta of the combined long/short portfolio is close to zero, uncorrelated to broad market movements and also not exposed to traditional market risk factors such as country, sector or market cap groupings.

What accounts for the excellent fund performance during times of significant market dislocation, like in 2020?

Through several years of iterating on things like data, staking and meta model composition, Numerai has been able to consistently construct a market portfolio where 80%+ of the return is derived from true idiosyncratic (stock selection) risk, rather than the usual factors that drive returns. During times of severe market dislocation like we saw in 2020, a beta-neutral portfolio that's also not exposed to traditional factors will significantly outperform both the market and other purported "market neutral" funds.

What is the current fund AUM and what is the expected fund capacity?

As of April 1, 2022, the AUM is roughly $71mm. We anticipate reaching $100mm in assets in the coming months and believe that the overall capacity for the strategy given the current structure is $500mm. However, because Numerai has ability to adapt things like the data set and the frequency with which we trade, capacity can be expanded to a multiple of that.


Minimum investment $1mm
Lockup 1 Month Notice, 1 Month Liquidity
Fund Capacity $500mm
Management Fee 1% annualized
Performance Fee 25% with high-water mark (Class A) 20% with high-water mark (Founders Class)

Portfolio Exposures

Gross & Net Exposure Gross: 500% - 600% (Net: ~0%)
Investment Products 100% Equities (Across market capitalizations)
Holding Period 2-4 Months (Weekly trading)

Portfolio Exposures

Maximum position size < 2% AUM, monitored daily
Trading Monitor for event risk and close or restrict security
Market Neutral Market, country and sector neutral
Factor Exposure Beta of ~0 with limited exposure to core style factors
Target Volatility < 10%
Industries All except Biotechnology and REITS

Service Providers

Fund Administrator SS&C
Auditor KPMG
Legal Counsel (US) Cole-Freiman and Mallon
Legal Counsel (Cayman) Maples
Prime Broker UBS
Tax Advisor KPMG
Compliance Consultant Titan Regulation