TD Bank Group announces multiyear relationship with Google

TD Bank Group announced Wednesday that it started using Google Cloud services, starting with the launch of TD Securities Automated Trading via serverless computing platform Google Kubernetes Engine.

The announcement marks a partnership between a major financial services provider and technology company, and a continuation of TD's strategy to move its core services and products to the public cloud. TD is the sixth largest bank in North America, with $1.91 trillion in assets as of January 31. Google Cloud has previously landed KeyBank, Wells Fargo, HSBC and others as customers.

"Our leadership and our talented, agile teams are supported by the relationships we have with our technology providers, including Google Cloud," said Greg Keeley, senior executive vice president of platforms and technology at TD, in a press release. "Together with Google Cloud, we are positioned well to continue to evolve our services and help power new and innovative banking experiences."

TD highlighted in the announcement that Google Kubernetes Engine "already supports" TD Securities Automated Trading, a fixed-income securities trading business TD purchased from Headlands Tech and rebranded in 2021. The product originally emerged from hedge fund Citadel about eight years ago.

Citadel used machine learning to analyze equities, said Matt Schrager, co-head of TD Securities Automated Trading, whose group now uses the product to determine fair bid and offer prices for munis and other fixed income instruments. Schrager spoke with Bond Buyer last year about how TD uses machine learning to determine fair prices on bonds.

As a largely buy-and-hold asset class, most of the $4.1 trillion outstanding universe of individual municipal bonds trade very infrequently. As such, price discovery is challenging in the muni market, according to Schrager.

To determine fair value for a bond that hasn't traded in weeks or months, "we need to correlate that bond to similar bonds that have traded recently," Schrager told Bond Buyer. "However, no two bonds in the market are quite alike, so we must be careful in this analysis to account for relevant differences."

Machine learning "helps us perform this kind of analysis in a rigorous way that both incorporates as much information as possible while also accounting for important differences between securities," he added.

This kind of analysis takes a gargantuan amount of computing power, hence the need for public cloud resources and the partnership between TD and Google Cloud, according to Dan Bosman, senior vice president and chief information officer for TD Securities and Treasury and Balance Sheet Management.

Google Cloud is "very well-suited" to TD's need for secure and scalable infrastructure that can support computationally intensive quantitative analysis, with a developer-friendly experience, according to Bosman.

"Google Cloud's capabilities have helped us grow TDSAT's trading volumes and portfolio size, and optimally serve our global clients," Bosman said.

In a blog post about the new partnership and promoting fixed income as an investment strategy, Schrager said Google Cloud has been "instrumental" in the success of TD's automated trading business.

"Google Cloud's offering has enabled us to construct a research platform that is one-of-a-kind in this space, with enough horsepower to drive the massive research workloads associated with our data-heavy approach," Schrager wrote.