Europe Fintech Trennding

Scorable launches second product release to enhance risk monitoring of corporate bonds amidst severe market volatility

Credit risk skyrockets in Covid-19 crisis, “fallen angels” on the rise

Scorable has launched its second product release to further enhance the scope and accuracy of its credit risk analysis, helping fixed-income managers make better investment decisions. The company’s innovative artificial intelligence (AI) solution enables asset managers to monitor corporate bonds and credit spreads and to anticipate rating changes before they occur or markets price them in.

With Covid-19 and the oil price collapse causing massive turmoil in financial markets, careful risk management is more important than ever. More than $92 billion of corporate debt fell to high yield from investment grade in March, and an end to the downward spiral is not in sight. Over the next few weeks, the number of issuers that lose their investment grade rating – so-called “fallen angels” – will continue to increase.

“Since the outbreak of the crisis, we see a significantly elevated credit risk in almost half of the companies we analyze. Particularly worrying for investors is that our analysis shows a high probability of a rating downgrade for more than a third of BBB-rated issuers. This requires close monitoring by institutional investors. Thanks to the latest updates to our Scorable model, portfolio managers can now predict future changes and fluctuations in corporate credit risk even more precisely,” says Oliver Kroll, CPO at Scorable and former leading portfolio manager for multi-billion Fixed Income portfolios.

With Scorable’s latest release, asset managers benefit from even more accurate and comprehensive risk monitoring, which helps them to outperform the market and manage their bond portfolio through crises. The company’s AI system now combines and contextualizes more than 350 quantitative and qualitative data variables, including FX data, new capital markets variables and indicators such as oil, gold, and country-level macroeconomic data.

Our analysis indicates that there will be another wave of corporate rating downgrades in the next couple of weeks. In the first ten days of April alone, several dozens of companies in our analysis portfolio were downgraded – our artificial intelligence accurately predicted 87% of these rating actions. This shows how using Scorable can help asset managers detect market dynamics due to Covid-19 early on, and thus make changes to their investment portfolio if necessary”, says Philippe Padrock, Managing Director at Scorable.

Scorable recently conducted a trading simulation on a EUR-denominated investment-grade corporate bond portfolio with medium credit risk and maturity profile. This demonstrated that using its AI-driven insights can help asset managers to outperform the market. Between 2017 and 2019, the strategy delivered an overall gain of 8.74% with a minimum portfolio turnover.

“Imagine, compared to some leading fixed income indices with similar risk profiles, our portfolio achieved a significant annualized outperformance of more than 30 bps. As a former portfolio manager, I would have been very happy to achieve this in the past zero-yield environment”, Kroll says.

And Robin Jose, CTO at Scorable adds: “Our recent trading simulation proves that using Scorable really gives portfolio managers an edge by enabling them to identify changes in credit risk and investment opportunities ahead of the market. With the ever-growing amount of data, our explainable AI can offer real added value in the decision-making process.”

Unlike black-box models which only show the input-output relationship, Scorable’s explainable AI approach allows users to intuitively understand the rationale behind the analysis and to see what factors drive changes in the risk score.


Related posts

2016 CNBC Disruptor 50 Features Klarna, Kabbage, Twilio, and Motif Investing

Manisha Patel

Blend Network: Fintech and Women’s Personal Finance

Nathan Gore

Hatstand partners with Sqreem to leverage statistical (machine) learning in the fight against financial crime

Manisha Patel