Overbond Integrates AI-Driven Margin Optimization Model

Overbond Integrates AI-Driven Margin Optimization Model

Overbond, the leading API-based credit trading automation and execution service in the global capital markets, has integrated an AI-powered margin optimization function into its existing automated trading system. As a result, traders can now train Overbond’s automated system to optimize their hit ratio according to the desired trading parameters of the desk. This increases the number of trade inquiries that traders can respond to without trader intervention.

The development of new financial products, the emergence of electronic all-to-all platforms and the rise of non-dealer liquidity providers using algorithmic and high-frequency trading have all reshaped fixed income trading. Now, fixed income traders face heightened volatility and evaporating liquidity against a backdrop of rate hikes, inflation, and recessionary concerns. Electronic and automated trading have become the new standards for meeting these challenges to credit desk profitability.

Until now, automated workflows have allowed traders to discover price and liquidity, but often required trader intervention to ensure trades adhered to the desired trade margins of the desk. This need for human intervention created a workflow bottleneck and prevented full automation for many trades. Overbond has achieved an advanced step forward in fixed income trading by fully automating the margin-optimization function within the Overbond automated trading system and data streams via API.

The Overbond margin optimization model optimizes the distance-to-cover based on the best executable price in RFQ protocol according to Overbond’s pricing model, COBI-Pricing LIVE. The margin model now incorporates variables that give insight into security, issuer and macro-level market risk and ensure that the automated margin is sensitive to intra-day risk movements. This data is collected from data vendors such as TRACE and includes bond-specific data such as coupon and amount outstanding, issuer-specific data such as quote counts and the volatility of the mid-price for the issuer, and sector-specific data such as the volatility of the bid-ask spread of the sector benchmark.

It’s necessary to account for trade size to fully automate trading because it’s an important factor in pricing and determining the desired margin. To address this, the Overbond margin model estimates the total market capacity per bond, which the model then uses to isolate the margin sensitivity to trade size.

Market risk and capacity are calculated from data available to all market participants, but desks gain their competitive advantage through the unique parameters they use to make their trading profitable. Any fully automated trading system must incorporate these parameters, so Overbond integrates desk-specific execution records into its analytics, allowing automated trading to adhere to the desk’s execution style, bias and margin approach.

“Achieving an optimal hit ratio is key for maximizing the P&L of sell-side desks and integrating auto-margin capabilities into the Overbond trading system enables true end-to-end automated trading that does not require human intervention,” said Vuk Magdelinic, CEO of Overbond.

Source: Overbond

Related articles

  1. Saphyre’s AI platform allows data to be entered once for simultaneous access.

  2. Customers can make more informed trading decisions and generate new alpha.

  3. Parsel automates the identification, extraction and digitisation of data to streamline processes.

  4. Saphyre uses AI technology to solve pre-trade setups and post-trade issues.

  5. Aquis Accesses Closing Auctions

    The venue matches counterparties using mathematical optimization.