Overbond launches buy-side model for spotting mispriced bonds

This image has an empty alt attribute; its file name is logo-cropped-11-news-300x66-1.png

Source: The Desk

Overbond has added a ‘rich-cheap’ model to its suite of AI fixed income analytics, designed to help buy-side desks generate systematic returns. Combining both static and dynamic analysis of multiple factors with AI,
the firm says its ‘rich-cheap’ model provides a quantitative method for screening for misprized fixed income securities. It is a mean-reversion valuation model designed to pre-identify bonds as rich ‘sell’ and cheap ‘purchase’ candidates based on proprietary Overbond valuation metrics and AI non-linear optimization.

“Overbond has harnessed AI and the wealth of new transaction information to bring quantitative trading to buy-side desks through an enhanced rich-cheap model. This new model provides insight well beyond the traditional rich-cheap analysis and is more powerful than what can be created through spreadsheet methods or factor analysis alone,” said Vuk Magdelinic, CEO of Overbond.

The rich-cheap model is offered as an add-on to Overbond’s COBI-Pricing LIVE, which has coverage of fixed income prices, liquidity scores and trading recommendations. With COBI-Pricing LIVE, fixed income traders can access an AI-driven suite that can potentially automate trade flow and improve liquidity risk, price monitoring and reporting. Overbond’s AI works for trades of any size and with varying liquidity profiles, and the system can be integrated with existing systems.

COBI-Pricing LIVE uses a multi-source data input and allows for the use of alternative data such as S&P Capital IQ Financial Statements. The full interoperability of COBI-Pricing LIVE via bilateral REST APIs potentially allows its AI algorithms to ingest, aggregate and process data from live and historical vendor feeds, internal historical records, OTC settlement layer volume records and voice transactions.

Overbond’s suite of AI algorithms is designed to analyze primary and agency trading routes and voice and electronically executed trades across multiple venues to which a fixed income desk is connected and counterparty types the desk trades with. This data aggregation is intended to boost coverage, precision and speed.