CQG, a leading global provider of high-performance technology solutions for traders, traders, brokers, hedgers and exchanges, today announced the completion of internal testing and proof-of-concept using live data on what the company believes is its first kind of artificial intelligence (AI) predictive model for marketers.
After extensive machine learning (ML) training in a backtesting environment, the company has just begun applying the technology to live data, with an extremely high level of predictive success in predicting future market movements.
Building on the firm’s deep expertise in analytics, mathematics and market intelligence, the new ML initiative aims to provide retail traders and market firms, including proprietary trading firms and hedge funds, with unprecedented tools to identify new trading and analysis opportunities , guiding trading strategies and managing their positions.
CQG has been exploring the field of artificial intelligence for the past year as part of solving its clients’ challenges, testing the technology in a state-of-the-art multi-platform lab. Last week, for the first time, the company tested its next-generation machine learning toolkit in a live trading environment and achieved 80% predictive accuracy – matching the results achieved in the back-testing environment.
CQG CEO Ryan Moroney said:
“In early 2023, we decided we wanted to do something different in machine learning and artificial intelligence that leveraged our unique position in the market by building our comprehensive database of historical trade data and analytics in a way that could help customers and our perspectives to analyze. predict and trade markets through a new lens. We built a lab and Kevin Darby – our VP of Execution Technologies – did a great job turning this effort into an exciting reality with results that have greatly exceeded our expectations.”
Darby said: “We first had to solve many real-world challenges, such as storing and curating terabytes of historical market data, while maintaining the ability to make microsecond decisions in real-time environments. We built bridges between the current Python-based ML infrastructure and the financial industry’s reliance on C++. We also needed to reformulate the traditional ML training pipeline to optimize genetic time series prediction to estimate conditional probability distributions in a mathematically satisfying and robust manner.”
He said the company’s live AI was consistently able to predict with 80% accuracy whether the next move in the E-mini S&P 500 futures contract would be up, down or unchanged.
Moroney said CQG has already identified multiple uses related to algorithms, graphs and research and is beginning to explore other applications with key partners.