Travis-CI Build Status


R Interface to the Numerai Machine Learning Tournament API

This interface allows download of tournament data, submit predictions, get user information, stake NMR’s and much more. Using the functions from this package end user can write R code to automate the whole procedure related to numerai tournament.

If you encounter a problem or have suggestions, feel free to open an issue.


Automatic submission using this package

1. Load the package.

2. Set working directory where data will be downloaded and submission files would be kept.

3. Set Public Key and Secret API key variables.

Get your public key and api key by going to and then going to Custom API Keys section under your Account Tab. Select appropriate scopes to generate the key or select all scopes to use the full functionality of this package.

Optional: If we choose not to setup the credentials here the terminal will interactively prompt us to type the values when we make an API call.

4. Download data set for the current round and split it into training data and tournament data

5. Generate predictions

A user can put his/her own custom model code to generate the predictions here. For demonstration purposes, we will generate random predictions.

6. Submit predictions for tournament and get submission id

The submission object should have two columns (id & prediction) only.

If you have an account with multiple models you should provide the model_id corresponding to model name you want to make submission against.

7. Check the status of the submission (Wait for a few seconds to get the submission evaluated)

8. Stake submission on submission and get transaction hash for it.

9. Release Stake and get transaction hash for it.

Performance functions

Users can now check performance across the following metrics: Reputation, Rank, NMR_Staked, Leaderboard_Bonus, Payout_NMR, Average_Daily_Correlation, Round_Correlation, MMC, Correlation_With_MM.

1. Display performance distributions

Create histograms of metric performance

2. Display performance over time

Create time series plots of metric performance

3. Display performance summary statistics

Create a table of summary statistics

Additional functions

1. Get account information

Get account information for the account whose API key and ID are entered, Check out the name of the return object to see what informations are included in the return and then subset the required information

2. Get Information for a round

Get information for a given round number.

3. Get current open round

Get closing time and round number for current open round

4. Get current leaderboard

Get V2 Leaderboard

5. Get User Performance

Get V2 User Profile

6. Run Custom GraphQL code from R: