DSK Bank had outgrown its existing risk scoring engine. Deploying sophisticated models was time-consuming and error-prone, while a lack of infrastructure for proper testing increased operational risk
DSK Bank is streamlining its model deployment process with IBM® SPSS® Modeler Gold—enabling models to move directly from development to testing and production without manual coding and with minimal IT support.
Approximately 6 times faster“time to yes”, reducing most loan approval times to just a few minutes
At least 50%of approvals will be fully automated, giving customers an instant decision
Reducesoperational risk by increasing control and auditability of model testing and deployment
Business challenge story
Harnessing predictive models to boost customer service
Operating in an increasingly competitive market, DSK Bank recognizes that customer service is one of its most important differentiators. The bank is constantly working on innovative ways to serve its clients faster and more efficiently, and sees predictive analytics as a key tool to help it automate processes and tailor its services to the needs of each client.
One of the most important areas where DSK Bank uses predictive analytics is its consumer loans approval process. Consumer loans make up approximately 50 percent of the bank’s retail loan portfolio, and have complex approval and underwriting requirements.
In the past, due to the lack of an integrated automatic process and the many manual checks involved, customers applying for a loan often had to wait up to several hours to learn whether their request had been approved. DSK Bank realized that by accelerating the process, it could greatly improve the customer experience and gain a significant competitive advantage over other banks in the Bulgarian market.
Boris Ederov, Head of Customer Risk Evaluation Systems at DSK Bank, comments: “We had already been using an automated risk scoring system as part of the approval procedure for almost ten years, but many other parts of the process were still manual. We wanted to use more advanced modeling techniques and integrate more of the business rules into the automated process, but our existing risk scoring system was not designed for this level of sophistication.”
The main issue with the existing system was deployment. The bank used IBM SPSS Modeler to design its models, but when a model was ready for production, the bank’s modeling team had to manually translate it into the input language used by the risk scoring system—essentially recoding the entire model from scratch. As the bank began using more sophisticated modeling techniques, this became increasingly time-consuming and error-prone.
“The breaking point came when we deployed a complex hybrid model using both logistic regression and decision trees in the old scoring system,” says Boris Ederov. “The implementation was time-consuming, and the system lacked good testing tools, which made it difficult to verify that we had implemented the model correctly. The operational risks had become too great, and we knew it was time to find a new approach.”
Improving model lifecycle management
DSK Bank decided to solve its testing and deployment problems by extending its use of solutions from the IBM SPSS Modeler Gold portfolio.
“We have been using SPSS Modeler to design our models for more than 10 years now, and we’re very productive with it,” says Boris Ederov. “We didn’t want to switch to a different platform that would be more difficult to use. Instead, we decided to replace the old scoring engine with SPSS Collaboration and Deployment Services and SPSS Analytical Decision Management.”
Working with IBS, a Bulgarian IBM Business Partner that specializes in helping clients achieve digital transformation, the bank delivered a successful pilot, which convinced the key stakeholders to migrate all existing models from the old engine to the new platform.
“The IBS team were very flexible and collaborative, which was vital because redesigning our consumer loans approval process was a real dive into the deep end. IBS helped us adapt the scope of the project to ensure we could deliver a new process that will meet all of our business goals.”
IBM SPSS Collaboration and Deployment Services provides a rigorous, standardized process for model implementation, enabling DSK Bank to enforce strict policies around the roles and processes involved in developing, testing and deploying models to production. Logging and security management is built into the platform, so it is easy for the bank to provide a complete history of the lifecycle of each model.
“With SPSS Collaboration and Deployment Services, the operational risks of moving a new model into production are almost non-existent,” says Boris Ederov. “We can be much more confident that everything has been properly tested and approved, and that our models are accurate and reliable.”
The solution also eliminates the need to rebuild models in a different language prior to deployment: the models move seamlessly from the development environment into testing and production, without requiring any recoding.
“With the new SPSS tools, the risk team owns the whole deployment process—we need almost no support from IT to get a new model into production,” says Boris Ederov. “That is empowering for us, and frees up time for the IT team to focus on other projects.”
Meanwhile, IBM SPSS Analytical Decision Management makes it easier for the bank to extend the automation of the credit risk assessment process beyond risk scoring. The team has implemented more than 50 business rules, which automate many aspects of the decision-making process and should eliminate a number of manual processes that back-office teams currently need to complete before a loan can be approved.
Improving customer service
As DSK Bank gets ready to retire its old risk scoring engine and put the new SPSS solution into full production, the bank is looking forward to seeing significant business benefits from its re-engineered consumer loan approval process.
“From an internal perspective, having a streamlined and well-governed model development and deployment process is going to save a lot of time and help us keep operational risk to a minimum,” says Boris Ederov. “But looking at the bigger picture, the real benefits of the project will come from its impact on customer service.
“SPSS will make the average loan approval process approximately six times faster, cutting the ‘time to yes’ to just a few minutes. We will be able to process almost half a million loan applications per year, of which more than 50 percent will be processed automatically, without any need for manual assessment.”
This means that when a customer visits a branch to apply for a loan, in the majority of cases they will be able to find out whether their application is approved almost instantly—with no need to wait for a phone-call or schedule a follow-up appointment.
Boris Ederov concludes: “IBM SPSS is playing a key role in the digital transformation of DSK Bank. Consumer loan approvals is a vital first step, and there is huge potential to embed predictive analytics into other key processes, such as customer retention and product recommendations. By providing a single platform for all our risk scoring and decision-making processes, SPSS gives us a powerful foundation for future growth.”
About DSK Bank
As Bulgaria’s oldest bank, DSK Bank leads the market in retail and private banking, and has a major presence in the corporate and small-to-medium enterprise banking markets. Part of the OTP Group, the bank serves around 3 million customers and operates the largest branch network in Bulgaria.
Take the next step
Founded in Bulgaria in 2003, IBS is an IT consulting, systems integration and software development company. Serving corporate and government clients, the company helps its clients adopt technology and harness data to drive digital transformation. To learn more about IBS, please visit ibs.bg.
IBM Analytics offers one of the world's deepest and broadest analytics platform, domain and industry solutions that deliver new value to businesses, governments and individuals. For more information about how IBM Analytics helps to transform industries and professions with data, visit ibm.com/analytics. Follow us on Twitter at @IBMAnalytics, on our blog at ibmbigdatahub.com and join the conversation #IBMAnalytics.