Building hedge signals.

Run by Data-scientists, Statisticians, Olympiad math medalists, ML engineers in more than 45 countries.

WHY
DataCrunch

More people more ingenuity.

Proprietary
data.

#1

We are gathering data at a very high pace thanks to our proprietary data streaming technology.

Collective
intelligence.

#2

1400+ data-scientists provide genuine and original predictions. This community intelligence improves prediction accuracy.

Portfolio management.

#3

We assemble predictions to identify stocks with expected excess returns and low volatility. Our portfolio is hedged against market and industry specific risk.

Why Crowdsourcing
Investment
Research

Tournaments
improve
prediction
accuracy.

Marcos López de prado and Frank J. Fabozzi - 2019

Avoid backtest overfitting

In tournaments, researchers can't run multiple backtest until finding a strategy that fits the past curve, but will obviously fail going forward.

Greater deapth
and breath for analysis

Tournament helps explore more investment opportu­nities and produce more forecasts per investment opportunity.

Avoiding False discovery

By obfuscating our dataset, data-scientists are not subject to selection biases or false assumptions.

Enhanced originality

Each data-scientist brings its unique skills and approach. It increases precision, originality and brings an edge to our signal.

DATA-SCIENTIST
TOURNAMENT

Get data,
train,
predict,
submit.

Get data.

#1

Train models.

#2

Predict targets.

#3

Submit predictons.

#4

START PREDICTING

Why competing

How does our community work

Researcher perform on a weekly basis their skills on encrypted datasets provided by DataCrunch and push their predictions.

These predictions are measured against the live market to identify the best performers. Those great models are ensembled in a meta-model that will be more precise then any of its constituents.

THE 
TEAM

The core team

We are engineers, finance geeks, former Wall Street analyst and Finance teacher at ESSEC, passionate about the underlying dynamics of our modern economies.

The community

Every week more and more data-scientists are joining and add skills to the project. The community is about 1400+ data-scientists from 45 differents countries as of today.

MEET THE TEAM

Subscribe to our monthly report.

Pre-order confirmed!

Thank you! Your pre-order has been received successfully. Our team will reach you with further details.
Well, something went wrong.
Please try again.