$ # 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" Build a model using the example Python and R scripts.
Everything you need to get started in one package.
#!/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") Build reputation to claim your place on the leaderboard.
Stake on your model to earn (or burn) cryptocurrency.
Trevor Paglen, CLOUD #865 Hough Circle Transform, 2019
Backed by Union Square Ventures and the co-founder of Renaissance Technologies.
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.