Financial services

Use Cases
  • Model development
  • Collaboration
  • Deployment and lineage for credit ratings
  • Better human and financial resource allocation
  • Faster response to clients, regulators and market events
  • Increased competitive advantage
  • Finance
  • Research
  • Model Governance

Data Science Tool(s): Jupyter, Python, R, SAS
Server/Cloud Infrastructure: Amazon Web Services

DBRS’s status as a premier credit rating agency requires that it delivers better models and credit scoring methodologies to the market faster.

Data Science at DBRS

“A competitive advantage of ours is market responsiveness. When somebody comes to us with a transaction they want to look at, the time it takes for us to respond is critical. Having tools in place that help us take quicker action on intelligence gives us an advantage” says DBRS CIO Sean Lensborn.

The company is leveraging the best operational and analytical tools to help it accelerate the time to market of its models at scale. One of those tools is Domino Data Lab. DBRS brought in Domino, running on Amazon Web Services (AWS), to serve as a centralized data science platform across the enterprise. Domino lets data scientists deliver high-value research faster by accelerating experimentation and increasing collaboration. At the same time, a centralized platform lets managers better allocate resources, and makes it easier for DBRS to satisfy regulatory requests by making work trackable, reproducible, and discoverable.


To compete with the biggest rating agencies, DBRS saw opportunities to enhance the pace of its quantitative research by optimizing processes in a few areas:

Model development and analytics. With data science teams geographically distributed across four offices (Toronto, New York City, London and Chicago), some duplication of effort was inevitable. DBRS recognized the value in identifying overlapping efforts and facilitating reproducibility to improve efficiencies.

Domino helps us deliver more value to the business by putting more powerful tools in the hands of our analysts.

Sean Lensborn, CIO at DBRS

Demonstration of governance. It is critical that DBRS’s rating decisions, model and methodology development have strict governance and auditability. Finding ways to automatically demonstrate governance would relieve researchers from having to compile documentation and could drive faster time to market of models.

IT procurement. Finding an easier way to accommodate data scientists’ varied needs for hardware, infrastructure and tools would alleviate pressure on IT and Engineering while helping data scientists be more productive.


DBRS initially evaluated Domino as a modeling collaboration platform, but upon seeing its governance capabilities decided to deploy it as the central platform for all data projects. Groups across the company including Finance, Research and Model Governance use Domino today, and that adoption is expected to expand to every product development team in the next six to 12 months.

The following Domino capabilities are most valued by DBRS:

Scalable compute
Data scientists can spin up high-powered workspaces with a single click, without needing help from Engineering. Domino’s integration with AWS was a big selling point.

Jinyoung Kim, senior vice president of Software Engineering at DBRS explained, “Domino exposed a lot of the higher computing options of AWS to the end users in a self-service way. That was a great benefit.”

Data scientists spanning the business’s four geographically distributed offices can easily discover past work and areas of expertise within the organization. Things that would have taken days to figure out on a local machine are resolved in hours by referencing something a colleague has already done, and employees learn from each other at a faster pace.

DBRS can also easily show all the data and code that went into analysis as Domino preserves the full experimental record automatically–-who was involved, what methodologies were attempted and discarded, when was it promoted to production and so on.

“Domino helps mitigate risk by not having to solely rely on humans to communicate, and simply capturing all that communication in the code base,” said Thomas Little, global head of Product Management for DBRS.

Data scientists get hands-on involvement from across the team without anyone needing to replicate environments. And because Domino is language agnostic, data scientists can work in their tool(s) of choice and business users have the ability to access powerful data science insights using tools they’re comfortable with (such as Microsoft Excel), without infrastructure headaches. As a result, adoption of the platform “spread like wildfire” according to Kim, growing from the 12 originally anticipated users to 50.

George Katsaros, DBRS’s vice president of Credit Policy, explained the platform as “a form of version control for projects. At the same time, it’s obviously a very powerful computation platform. The fact that we can combine those two elements at the same place is extremely efficient.”

“It’s a time saver,” said Michael Sinclair, a quantitative analyst for the firm. “You don’t have the usual difficulties of following a rigorous documentation program; you can just do your work and it’ll track for you. You can go back and change something if you need to, you can move things around, or you can tag somebody if you need help. It’s a centralized hub.”

DBRS also valued the business partnership Domino offered. From the initial trial and environment configuration through proving value to DBRS’s executive team and listening to product roadmap input post-sale, Domino demonstrated its ability to be a strategic adviser throughout DBRS’s data science journey.

The Domino Effect

Users across the company are benefiting from the Domino implementation.

Data scientists save time and can take on previously impossible projects, by leveraging elastic hardware in AWS. They can experiment at the speed of thought, without getting slowed by the prior process to meticulously document everything they do. This saves time while fueling higher quality work.

Heads of data science and quantitative research are delivering.“We’ve identified projects where multiple people in the organization were trying to tackle the same problem,” said Kim. “We’re figuring out who’s the best fit to actually tackle that problem and avoid duplication. A benefit is that we’ll produce even better results.”

Analysts use the output for credit decisions on the front lines and provide a clear feedback loop to data science teams based on their subject matter expertise.

“Domino helps us deliver more value to the business by putting more powerful tools in the hands of our analysts,” said Lensborn.

Regulators benefit from faster response and even greater visibility into DBRS’s credit scoring methodologies.

Human resources can leverage the experience to recruit top data science talent, offering a best-of-breed platform that any data scientist should be comfortable using.

As a result, DBRS delivers faster research outcomes with Domino, accelerating the pace at which it can respond to clients and bring new data sources and credit methodologies to market.

Domino Data Science Platform

For more info, please Contact Us.