meets artificial intelligence

We are building the next generation of investing: decentralized, systematized, and democratized.

LEARN MORE

I am a

Open simulation ↗ · Historical simulation with parameters selected using past results. Fees and funding included; market impact excluded. Not live performance.

Machine learning for investing

Develop quantitative models on our datasets and submit predictions to an open competition. Compete against the world's best ML experts, measure true out-of-sample performance, and simulate the meta-model as live portfolios.

crowdcent_challenge.pyPython
import crowdcent_challenge as cc
client = cc.ChallengeClient()
data = client.download_inference_data()
preds = model.predict(data)
client.submit_predictions(preds)
JOIN THE CHALLENGE READ DOCS

Each point is a feature extraction from a single write-up; similar text clusters in three independent 3D UMAPs. Source: synthetic data

Write-up extraction

Select a point to read the corresponding extraction.

Fundamental research

We extract meaning from investment write-ups (e.g. catalysts, risks, and competitive advantages) and combine them with financial data to train predictive models.

Contribute your research through our partner communities, including SumZero.

EXPLORE OUR METHODOLOGY
From independent forecasts to portfolio weights An abstract matrix shows different models ranking the same assets. Their forecasts combine into one collective signal, which informs positive and negative portfolio weights around a common zero axis. This is an illustration of the process, not investment performance.

Investment management

CrowdCent brings independent research and predictive models into a systematic investment process. Contributions are evaluated over time and combined into a collective model that informs portfolio construction.

CONTACT THE INVESTMENT TEAM

How it works

Analysts share investment research across our network of partner communities. CrowdCent transforms these unstructured insights into data for a global community of data scientists to build predictive models. The result is a meta-model that captures the best of both human and machine intelligence, directing real world capital towards the collective's favorite opportunities. Anyone can put the meta-model to work in the on-site Simulator: sweep parameters, blend sleeves, and stress-test strategies against out-of-sample holdouts on real Hyperliquid data.

A diagram that describes how the CrowdCent platform works.

Participate in CrowdCent

Build models, contribute research, or discuss an investment partnership.

GET IN TOUCH