The increased need for buy- and sell‑side firms to more efficiently manage fixed income execution costs has given rise to greater adoption of electronic trading and wider use of automated trade processes and strategies. The lack of liquidity in bond markets has traditionally made predicting bond prices difficult. To help buy-side traders be more confident as price makers, and to support best execution policies, MarketAxess has developed Composite+, a proprietary algorithmic pricing engine for corporate bonds that leverages a range of proprietary and industry data sources, with updates up to every 15 seconds.
Composite+ combines public data from the Trade Reporting and Compliance Engine of the Financial Industry Regulatory Authority with MarketAxess proprietary data from its trading platform and Trax post-trade pre-settlement trade matching and regulatory reporting system for over-the-counter markets. The solution applies artificial intelligence (AI) and machine learning to predict accurate two-way reference prices for more than 24,000 bonds globally. When the most proximate signals are missing, the Composite+ algorithm can still learn to triangulate less predictive features successively.
Prices are updated every 15 to 60 seconds depending on liquidity of instruments, with nearly 20 million market levels generated per day covering 90–95% of trading activity in relevant markets. In December 2017, more than half of all pre-trade Composite+ market levels were less than 1.1 basis point (yield) away from the executed level, the company claims.
Composite+ is designed to support a variety of trading functions such as pre-trade price discovery, liquidity provision, transaction cost analysis, auto-execution and crossing. The pricing engine is incorporated into all aspects of MarketAxess’s trading workflow, including within its request for quote inquiry screen. It is integrated into the company’s BondTicker and Axess All web-based data platforms, as well as its Open Trading all-to-all marketplace. Composite+ can also be streamed directly to clients’ systems via a financial information exchange application programming interface feed.
“MarketAxess has progressive technology and a clear purpose. The scope of the product is narrow, but it does exactly what it sets out to do.”
“Smart AI-based toolkit. Interesting integration with trading and data platforms in the past 12 months.”
“Intelligent application of machine learning to the challenge of fixed income pricing, accessing comprehensive data sources.”
David Krein, global head of research at MarketAxess, says:
“Buy- and sell-side trading desks are increasingly needing to efficiently access liquidity and demonstrate best execution. Buy-side traders are also taking on new roles and becoming price makers, which requires key information at their fingertips. Our Composite+ pricing engine is helping fulfil these requirements with pricing data on more than 24,000 bonds updated up to every 15 seconds. We are starting to scratch the surface of the possibilities for AI and how it can transform data in the trading workflow – the intersection of data, trading and technology is a key part of the market evolution.”