Technology solutions business CQG has unveiled a new trading toolkit, with a “first of its kind” AI predictive model for traders which incorporates live data to predict futures market moves.
Ryan Moroney
Following internal testing and proof-of-concept using live data, CQG has confirmed that the system has been successful in a live trading environment.
“Following extensive machine learning (ML) training in a back-testing environment, the firm just started applying the technology to live data, with an extremely high level of predictive success in anticipating futures market moves,” said CQG in a statement.
The new machine learning offering is aimed at retail traders and buy-side firms such as proprietary trading firms and hedge funds.
Ryan Moroney, chief executive of CQG said: “In early 2023, we decided we wanted to do something different in machine learning and AI that leveraged our unique position in the market, building off our comprehensive database of historical trade data and analytics in a way that could help our clients and prospects analyse, predict and trade markets through a new lens.”
During use in a live trading environment, the model achieved 80% predictive accuracy according to CQG, with the results attained matching those in the back-testing environment.
Specifically, the AI was “consistently” able to predict whether the next movement in the E-mini S&P 500 futures contract would be up, down or unchanged.
In addition, CQG claims to have already identified multiple uses related to algos, as well as charting and research. Expectations are for the firm to also start exploring other applications with key partners.
Kevin Darby, vice president of execution technologies at the company, explained that the firm had had to solve various real-world challenges during development which included “storing and curating terabytes of historical market data while retaining the ability to make decisions in microseconds in real-time environments”.
Darby added: “We built bridges between the current ML infrastructure, based on the Python language, and the reliance of the financial industry infrastructure on C++. We also needed to recast the traditional ML training pipeline to optimise for generative time series prediction to estimate conditional probability distributions in a mathematically satisfying and stable way.
“[…] What we’ve built is portable. 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. They can then use CQG for charting and trading with those models.”