It is clean and regularized, designed to be usable right away. Obfuscated, so it can be given out for free.
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.
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_csv("numerai_training_data.csv").set_index("id")
# tournament data contains features only
tournament_data = pd.read_csv("numerai_tournament_data.csv").set_index("id")
feature_names = [f for f in training_data.columns if "feature" in f]
# 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(training_data[feature_names], training_data["target"])
# submit predictions to numer.ai
predictions = model.predict(tournament_data[feature_names])
predictions.to_csv("predictions.csv")
An example of a complete Numerai model written in Python.
id | prediction |
---|---|
n60dffdaceb7e467 | 0.25 |
nadaeef0214b84a8 | 1.00 |
nb13883520a4344f | 0.25 |
n423766c5a4fa42a | 0.75 |
n252b14301e46a31 | 0.25 |
n75a5baf93a624cc | 0.00 |
n2ff91086716e413 | 1.00 |
Example target predictions.
Build reputation to claim your place on the leaderboard. Stake on your model to earn (or burn) cryptocurrency. $40,572,172 in NMR has been paid to data scientists.
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.
Backed by Union Square Ventures, the co-founder of Renaissance, and the co-founder of Coinbase.
General enquiries | contact@numer.ai |
Community and support | discord.gg/numerai |
Careers | AngelList |
Investor inquiries | investing@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.