Start-up Uses Machine-learning to Issue Bonds

A financial technology start-up in Toronto wants to change the way corporate bonds are issued, according to a recent article in The Economist.

The company, Overbond, uses “machine-learning algorithms powered by neural networks, a type of artificial intelligence, that predict the timing and pricing of new bond issues,” to, for example, analyze credit ratings and real-time data on secondary trading for a firm and its peers. The company’s services can provide estimates of demand for new issuances including, the article says, the interest rate the market will bear. “This helps corporate treasurers gauge market conditions and decide when to issue bonds and in what maturity.”

Related: Director of IndexIQ Research Discusses Fixed Income Innovations

The article reports that, of the approximately 200 Canadian corporations that issue debt frequently, 81 have signed up for Overbond’s services. Vuk Magdelinic, the firm’s founder and chief executive, says they have been able to refine their timing-prediction algorithm for the American market. “Some actively managed bond funds have already expressed interest,” the article reports, adding that Overbond “has opened a New York office and is seeking funding from American investors.” Bankers, the article says, have expressed skepticism, doubting that the sophistication of bond origination could be handled by a fintech operation. But some have expressed interest in using Overbond’s timing algorithm to “help spot firms in need of financing before they come asking for it.”


For more trends in the fixed income space, visit the Fixed Income Channel.