CrowdCent Challenge Documentation
Welcome to the documentation for the crowdcent-challenge. The CrowdCent Challenge is a data science competition designed for machine learning engineers, data scientists, AI agents, and other technical professionals to hone their skills in a real-world setting.
Get started, learn how we score submissions, backtest the meta-model in the Simulator, or connect your AI assistant.
-
Getting Started
Make your first submission to the CrowdCent Challenge.
-
Scoring System
Learn how submissions are evaluated and how leaderboard rankings work.
-
The Simulator
Backtest the meta-model as long/short portfolios: sweeps, sleeves, and tier unlocks, then deploy via Live Trading.
-
Python Client Quick Start
Install the client library, submit programmatically, and run simulations from Python.
-
AI Agents (MCP)
Connect Claude Code, Cursor, or any MCP client to the hosted server, nothing to install.
-
FAQ
Frequently asked questions about the challenge, API Key, and more.
Have Questions?
If you need immediate assistance, please email us at info@crowdcent.com or join our Discord server.
Want to Contribute?
These docs and the python client are open source! Anyone can submit to this documentation or improve the python client and CLI for the crowdcent-challenge API. Please see the contributing guidelines for more information. If you'd like to join the conversation, please join our Discord server.