The new offering leverages machine learning to help traders better manage strategies and positions.
CQG has unveiled a predictive trading model toolkit that applies machine learning (ML) technology to live data and is intended to help traders better manage strategies and positions.
The announcement follows what CQG officials say was a successful, “first-of-its-kind” proof-of-concept (POC) testing effort, and then a reality check in a live-trading environment.
In the live trading environment, the toolkit had “80 percent predictive accuracy — matching the results attained in the back-testing environment,” according to CQG. ML is based on artificial intelligence (A.I.) technologies.
In particular, the toolkit had an “extremely high level of predictive success in anticipating futures market moves,” according to CQG officials. The toolkit predicted with “80 percent accuracy whether the next movement in the E-mini S&P 500 futures contract would be up, down or unchanged.”
Ultimately, the goal is to leverage CQG’s “experience in analytics, mathematics and market intelligence,” and offer retail traders, buy-side firms, proprietary trading firms, and hedge funds “tools for identifying new trading and analytics opportunities,” officials say.
CQG has been exploring A.I. for a year by “testing the technology in a state-of-the-art multi-platform lab,” officials say.
“We built a lab, and Kevin Darby – our vice president of execution technologies – has done an extraordinary job of turning that effort into an exciting reality with results that have significantly surpassed our expectations,” says Ryan Moroney, CEO of CQG, in a prepared statement.
“We first had to solve multiple real-world challenges, such as storing and curating terabytes of historical market data while retaining the ability to make decisions in microseconds in real-time environments. We built bridges between the current ML infrastructure, based on the Python language, and the reliance of the financial industry infrastructure on C++,” Darby says in a statement.
“We also needed to recast the traditional ML training pipeline to optimize for generative time series prediction to estimate conditional probability distributions in a mathematically satisfying and stable way,” Darby adds.
CQG has identified multiple uses of its new toolkit “related to algorithms (algos), charting and research and is starting to explore other applications with key partners,” officials say.
“What we’ve built is portable,” Moroney says. “We can give a firm a set of encrypted files, and they can see how our technology predicts moves in liquid futures contracts with a high rate of accuracy. They will be able to use our ML lab, apply cloud computing resources, and create their own models, either leveraging our models as foundational or making their own from scratch using our historical data and ML toolkit.”
CQG provides a variety of trading technology solutions for market makers, traders, brokers, commercial hedgers, and exchanges.
Need a Reprint?