Tournament Overview
At the core of Numerai is a data science problem - the problem of predicting the stock market.
In the provided training_data, each id corresponds to a stock with a set of obfuscated features. Thetarget represents future performance. Rows are grouped into eras that represent different points in time.
Your goal is to train a machine learning model to predict the target given new features.
Read the analysis and tips notebook for an in-depth exploration of the dataset.
Below is an example how to train a model on the training_data to make predictions on the tournament_data.
Check out the example-scripts repo for more advanced examples.
import pandas as pdfrom xgboost import XGBRegressor​# training data contains features and targetstraining_data = pd.read_csv("numerai_training_data.csv").set_index("id")​# tournament data contains features onlytournament_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 datamodel = 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.aipredictions = model.predict(tournament_data[feature_names])predictions.to_csv("predictions.csv")
Every Saturday at 18:00 UTC, a new round begins and new tournament_data is released. Submit your predictions to Numerai to enter the tournament.
The submission deadline is Monday 14:30 UTC. Late submissions will not be eligible for payouts.
Use our tools and libraries to connect with our GraphQL API.
Your submission is scored on the correlation between your predictions and the true targets. The higher the correlation the better.
# method='first' breaks ties based on order in arrayranked_predictions = predictions.rank(pct=True, method="first")correlation = np.corrcoef(labels, ranked_predictions)[0, 1]
Your submission will also be scored on your metamodel contribution or mmc.
See the metamodel contribution section for details.
You can stake on your submission to start earning payouts. You can either stake on correlation or corr plus mmc.
You can start participating in Numerai without staking to learn more about the tournament and about your model(s)' performance. When you feel confident in your model(s), you can attach some stake to it. The minimum stake value is 0.01 NMR.
Staking requires you to lock up NMR in an Erasure smart contract agreement. This gives Numerai the ability to burn your stake if your model performs poorly.
You earn or burn a percentage of your stake based on the score you are staking on. For example, if you stake 100 NMR on correlation and your score was +0.05, then you will earn 5% of 100NMR = 5NMR. The maximum you can earn or burn is 25% of your stake each round.
corr_payout = stake * clip(corr, -0.25, 0.25)​mmc_payout = stake * clip(corr + mmc, -0.25, 0.25)
See the staking and payouts section for details.
Each submission will receive daily updated scores starting from the first Thursday after the submission deadline to the Wednesday 4 weeks after. For example, if you made the blue submission on Sun 7th, you will receive your first score on Thur 11th and your final score on Wed 7th of the next month.
If you staked on your submission, you will also receive daily updates on your payouts. But only your final score and final payout will count.
Your rank on the leaderboard is based on your reputation, which is a weighted average of your correlation scores over the past 20 rounds.
See the reputation section for details.
Need help?
Find us on RocketChat for questions, support, and feedback!
