ADIA Lab Market Prediction Competition
  • The tournament
    • Overview
    • Timeline
    • Evaluation
    • Data
    • Prize
  • Requirements
    • Code Requirements
    • The Submission Code Interface
    • Resource Limit
    • Whitelisted Libraries
  • Participate
    • How to participate
    • Create an account
    • Setup
    • Your working directory
    • A basic but functional solution
    • Testing your code
    • Submitting
    • Get a score on the leaderboard
    • Run in the Cloud Environment
    • Monitoring your Cloud Runs
    • Out-of-Sample Submission Selection
    • Out-of-Sample Evaluation Phase
    • Advanced Material
    • Known Issues
Powered by GitBook
On this page
  1. Participate

Out-of-Sample Submission Selection

PreviousMonitoring your Cloud RunsNextOut-of-Sample Evaluation Phase

Last updated 1 year ago

During the Out-of-Sample, your code will be run every week on a submission of your choice.

By default the system selects the best successful run.

If and only if you want to select another submission than the best run, use the Out-of-Sample Parameters Selector.

Parameters

Name
Description

Submission

Submission to use during the Ouf-of-Sample.

Runtime Type

Whether to use a CPU or a GPU runner.

Train Frequency

Frequency of which your submission's train function will be called. The frequency is a modulo on the moon, not loop.

Force First Train

Force the call of the submission's train function at the first loop. Some submission with a resources folder are not working correctly without having their train function called at least once.