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

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

Numerai

 

AQR EMN

 

Aurum Quant EMN Index

 

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 ›

Source: Aurum, Bloomberg

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.

Investment Process

1 Research and 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 the data science community.

2 Data Tournament

Datasets are made available to our community of data scientists who compete to create the best predictive models in a tournament. Data scientists stake their best models with our cryptocurrency, NMR.

3 Meta Model

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

4 Portfolio Construction

Model is fed into Numerai’s optimization engine to construct the optimal risk penalized, market neutral portfolio.

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
Example image

Learn more about the tournament

Watch Building the Meta Model on Numerai and learn how Numerai combines thousands of predictions into one meta model.

See the tournament of competing data scientists here.

Terms

Minimum Subscription $1 million
Redemptions Monthly with 30-day notice
Lock-up No lock-up
Management Fee 1% annualized
Performance Fee 25% with high-water mark

Portfolio Exposures

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

Risk Management

Maximum position size < 1.5%, 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

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