Trevor Paglen, CLOUD #865 Hough Circle Transform, 2019

Architect an AI scientist

Use frontier AI to predict the stock market.

Achieve Grandmaster status.

$ # clone example-scripts, install MCP, and prompt Codex$ git clone git@github.com:numerai/example-scripts.git$ cd example-scripts && curl -sL https://numer.ai/install-codex-mcp.sh | bash$ codex exec --yolo "find the best neural network architecture to predict target ender"

Start with hedge fund quality data.

It is clean and regularized, designed to be usable right away. Obfuscated, so it can be given out for free.

iderafeature0...featureXtarget
n2b2e3dd163cb422era10.75...0.000.25
n177021a571c94c8era11.00...0.250.75
n7830fa4c0cd8466era10.25...1.000.00
nc584a184cee941bera10.25...0.001.00
nc5ab8667901946aera10.75...0.250.25
n84e624e4714a7caera10.00...0.751.00

Each id corresponds to a stock at a specific time era. The features describe the various quantitative attributes of the stock at the time. The target represents an abstract measure of performance a fixed number of weeks into the future.

Apply machine learning to predict the stock market.

Build a model using the example Python and R scripts.
Everything you need to get started in one package.

 
Staked models
#!/usr/bin/env python
""" Example classifier on Numerai data using a xgboost regression. """

import pandas as pd
from xgboost import XGBRegressor

# training data contains features and targets
training_data = pd.read_parquet("train.parquet").set_index("id")
features = training_data.filter(like="feature_")
target = training_data["target"]

# train a model to make predictions on tournament data
model = XGBRegressor(
  max_depth=5,
  learning_rate=0.01,
  n_estimators=2000,
  colsample_bytree=0.1
)
model.fit(features, target)

# submit predictions to numer.ai
predictions = model.predict(features)
predictions.to_csv("predictions.csv")

An example of a complete Numerai model written in Python.

idprediction
n60dffdaceb7e4670.25
nadaeef0214b84a81.00
nb13883520a4344f0.25
n423766c5a4fa42a0.75
n252b14301e46a310.25
n75a5baf93a624cc0.00
n2ff91086716e4131.00

Example target predictions.

Submit models to predict
the stock market.

Build reputation to claim your place on the leaderboard.
Stake on your model to earn (or burn) cryptocurrency.

 
Paid to data scientists

Learn More

Learn how Numerai combines thousands of models into one meta model to predict the stock market.

Numerai data scientists stake their best models with our cryptocurrency, NMR. Watch the video introducing NMR to our community.

Introduction to Numerai Signals, a tournament for data scientists who have their own data.

Trevor Paglen, CLOUD #865 Hough Circle Transform, 2019

Join the network and build the world’s last hedge fund.

Backed by Union Square Ventures and the co-founder of Renaissance Technologies.

Receive updates about Numerai

 
General enquiriescontact@numer.ai
CareersWellfound
Investor inquiriesinvesting@numer.ai

Note: Numerai runs a quantitative global equity market neutral hedge fund which is unsuitable for most investors. The fund is designed for institutional investors though some high net worth accredited individuals may qualify.