Akbank Uses Prescriptive FICO Analytics to Increase Credit Card Approvals by 45% and Limits by 60%

First Turkish retail bank Wins FICO® Decisions Award for AI, Machine Learning and Optimization Using FICO Decisions Optimization Technology


Strong points:

  • Akbank complied with complex regulations while increasing credit card approvals by 45% and approved limits by 60%

  • Akbank will realize a 129% increase in profits from the solution

  • Akbank Won a 2022 FICO® Decisions Award for AI, Machine Learning and Optimization

Akbank, one of Turkey’s largest retail banks, has improved the way it offers consumers new credit cards and credit limit increases by leveraging mathematical optimization and stock modeling/ effects from the world leader in FICO analysis. Using FICO prescriptive analytics helps the bank comply with stringent national laws regarding credit offerings while increasing credit card approvals by 45% and credit limits by 60%.

For his achievements, Akbank won a 2022 FICO® Decisions Awards for AI, Machine Learning and Optimization.

More information: https://www.fico.com/en/products/fico-decision-optimizer

“Growth of credit card wallet market share and revenue depends on the level of credit limits approved for customers”, said Serhan Pak, Senior Vice President of Retail Lending and Advanced Credit Analytics at Akbank. “However, credit loss is also affected by assigned limits. Therefore, limit assignment is an area that we believe would benefit from optimization.”

Turkey’s market regulator stipulates that a consumer’s total credit card limit cannot exceed twice their monthly income in the first year and four times their income after the first year. This rule meant that Akbank had to include existing credit cards from other banks in its optimization model.

Akbank’s profit model also had to take into account the many options available to customers in the market, such as paying by installments, deferring payments or withdrawing cash advances with installment repayment options. This meant that from a profit perspective, even though a credit card is a single product, it can behave like four different products.

“The profit model of the product turned out to be very complex”, said Pack. “In addition to regulatory and product considerations, we had to take into account pandemic lockdowns, which impacted the number of inquiries, customer profiles and channel mix. Provisions were also made for the impact of rising inflation on revenue calculations and historical earnings.”

FICO® Decision Optimizer was used to design strategies and set limits for initial line of credit (ICL) and increase line of credit (CLI) transactions at Akbank. The project aimed to help the bank understand and model the likely reactions of customers to various offers and what the trade-offs would be when incremental changes were made to different business objectives.

The application of action/effect modeling was a new methodology for Akbank. This improved the quality of decisions by incorporating customer feedback into decision models, leading to improved forecasting.

“A major challenge was the legal caps imposed by the regulator,” said Pack. “There was a high risk of change in the Covid era that we had to plan for. To overcome this, the team came up with the solution that combines both uncapped and capped flows in the same project, which does not hadn’t been done before in Decision Optimizer.”

Legal caps on a consumer’s revenue-to-limit ratio are applied as a consideration, but not as a direct cap on the optimized limit, during the optimization process. This provides greater flexibility and speed because the optimization results do not depend directly on these caps but take into account their impact when the strategy is deployed in the real world. Through this process, regulatory changes can be implemented and managed quickly and their impact assessed. This dual structure allows Akbank to be more flexible to market changes compared to competitors who do not use uncapped optimized decision flows.

The most important benefit of optimization was the ability to see the trade-offs between different business goals. A framework was developed in Python to examine and visualize the results in great detail, which allowed Akbank to compare different strategies. Using techniques such as machine learning, action/effect modeling, optimization and extensive use of tools such as Python, Akbank has created a more analytical, flexible and integrated approach to strategic management.

“It was a conceptually difficult problem”, said Graham Rand, operational researcher and publisher of Impact and one of the judges for the FICO Decisions Awards. “The nature of what Akbank was targeting and the fact that they had to consider competing banks in Turkey, as well as optimizing for both capped and uncapped scenarios, demonstrates their decision-making sophistication.”

The credit card optimization project has been a great success for Akbank. The optimized strategies enabled the bank to comply with complex regulations while increasing credit card approvals by 45% and approved limits by 60%. This was achieved while maintaining the same credit losses. Akbank expects to realize a 129% increase in profits from its credit card portfolio using the solution.

“In today’s world, consumers have more options and the stakes are high when it comes to capturing more market share,” said Nikhil Behl, Director of Marketing at FICO. “Akbank has demonstrated how a lender can leverage its analytics capabilities with optimization to increase loan profits.”

About Akbank

Akbank’s core business is banking business, which includes corporate and investment banking, commercial banking, SME banking, retail banking, payment systems, treasury transactions and private banking, and international banking. In addition to traditional banking activities, the Bank also carries out insurance agency activities through its branches, on behalf of Ak Insurance and AgeSA Life and Pensions A.Ş.

With a strong and extensive national distribution network of 716 branches employing over 12,000 employees, Akbank operates from its headquarters in Istanbul and 19 regional branches across Turkey. In addition to providing services in branches, its traditional delivery channel, Akbank also serves approximately 18 million customers through Akbank Internet, Akbank Mobile, call center, approximately 5,000 ATMs and more than 600,000 terminals. point of sale.

About the FICO® Decisions Awards

The FICO Decisions Awards recognize organizations that achieve outstanding success using FICO solutions. A panel of independent judges with deep industry expertise evaluates nominations based on measurable improvement in key metrics; demonstrated use of best practices; the scale, depth and scope of the project; and innovative uses of technology. The 2022 judges are:

  • Sidhartha Dash, research director at Chartis

  • Paul Deal, Head of Risk, Mortgages at Westpac (previous winner)

  • Senthil Erulappan, Director, Merchant Product Engineering, Risk and Collections at FIS

  • Armand Junior, Managing Director, Risk and Compliance at Dock (previous winner)

  • Sheila Leverone, head of marketing at eDriving (previous winner)

  • Sibulelo Ncamani, head of operational risk and governance at Absa Bank (former winner)

  • Graham Rand, operational researcher and publisher of Impact

  • Dinesh Suresh, Manager, Digital Constructs for Consumer Secured Loans at OCBC Bank (former winner)

About FICO

FICO (NYSE: FICO) powers the decisions that help people and businesses around the world thrive. Founded in 1956 and based in Silicon Valley, the company pioneers the use of predictive analytics and data science to improve operational decisions. FICO holds more than 200 U.S. and foreign patents on technologies that increase profitability, customer satisfaction, and business growth in financial services, manufacturing, telecommunications, healthcare, retail, and many other industries. . With FICO solutions, businesses in more than 120 countries are doing everything from protecting 2.6 billion payment cards from fraud, to helping people get credit, to ensuring that millions of planes and rental cars are in the right place at the right time.

Learn more at www.fico.com.

FICO is a registered trademark of Fair Isaac Corporation in the United States and other countries.

See the source version on businesswire.com: https://www.businesswire.com/news/home/20220621005032/en/


Wendy Harrison/Parm Heer/Matthew Enderby
[email protected]
0208 977 9132

About Ian Crawford

Check Also

DBS Vickers recommends buying “TIDLOR”

DBS Vickers recommends buying “TIDLOR” DBS Vickers recommends buying “TIDLOR” with a target price of …