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 scientists perform on a weekly basis their AI skills on datasets provided by DataCrunch and push their predictions.
These predictions are measured against live market data to rank data scientists.
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. Over the years we became savvy investors by subscribing to academically researched or hedge fund reviews and reimplementing their strategies.
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.
.png)