Leading Turkish Retail Bank wins FICO® Decisions Award for AI, Machine Learning & Optimization Using FICO Decision Optimization Technology
LONDON, June 21, 2022†BUSINESS WIRE†FICO (NYSE: FICO):
Akbank has complied with complex regulations while credit card approvals have increased by 45 percent and limits have been approved by 60 percent
Akbank realizes a 129 percent profit increase from the solution
Akbank has won a FICO® Decisions Award 2022 for AI, Machine Learning & Optimization
Akbank, one of the largest retail banks in Turkey, has improved the way it offers consumers for new credit cards and credit limit increases by leveraging mathematical optimization and action/impact modeling from global analytics leader FICO. The use of prescriptive FICO analysis allows the bank to comply with strict state laws surrounding credit offerings, while increasing credit card approvals by 45 percent and credit limits by 60 percent.
For his achievements Akbank won a 2022 FICO® Decisions Award for AI, Machine Learning & Optimization.
More information: https://www.fico.com/en/products/fico-decision-optimizer
“Growing market share and revenue in the credit card portfolio is dependent on the level of credit limits approved to customers,” said Serhan Pak, SVP of retail lending & advanced credit analytics at Akbank. “However, credit loss is also affected by the limits assigned, so assigning limits is an area that we thought would benefit from optimization.”
The Turkish market regulator stipulates that the total limit of a consumer’s credit card cannot exceed twice the monthly income in the first year and four times the 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 numerous options available to customers in the market, such as installment payment, deferral of payments or the withdrawal of advances with installment options. This meant that from a profit point of view, although a credit card is a single product, it can behave like four different ones.
“The revenue model of the product turned out to be very complex”, said Business suit. “In addition to regulatory and product considerations, we had to account for pandemic lockdowns, which impacted application numbers, customer profiles and channel mix. Provisions were also made for the impact of rising inflation on income calculations and historical revenues.”
FICO® Decision Optimizer was used to design strategies and set limits for initial lines of credit (ICL) and credit line increases (CLI) at Akbank. The project was designed to help the bank understand and model likely customer responses to different offerings and what the trade-offs would be when incremental changes were made to different business goals.
Applying action/effect modeling was a new methodology for Akbank. It led to an improvement in decision quality by integrating customer responses into the decision models, enabling better predictions.
“A major challenge was the regulatory limits imposed by the regulator,” said Business suit. “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 flow in the same project, which has not been done before in Decision optimization.”
The legal limits on a consumer’s income-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 as the optimization results do not directly depend on these limits, but consider their impact for when the strategy is implemented in the real world. This process allows for rapid adoption and management of regulatory changes and assessment of their impact. This dual structure allows Akbank to deal with market changes more flexibly compared to competitors who do not use optimized unrestricted decision flows.
The main benefit of optimization was the ability to make trade-offs between different business goals. A framework was developed in Python to examine and visualize the results in great detail, allowing 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 strategy management approach that is more analytical, flexible and integrated.
“This was a conceptually difficult problem,” said Graham Rand† operational researcher and editor of Influence and one of the judges of the FICO Decisions Awards. “The nature of what Akbank focused on and the fact that they had to consider competing banks in Turkey, as well as optimizing for the capped and uncapped scenarios, demonstrates their sophisticated decision-making.”
The credit card optimization project has been very successful for Akbank. The optimized strategies allowed the bank to comply with complex regulations, while credit card approvals grew by 45 percent and approved limits by 60 percent. This was achieved while credit losses remained flat. Akbank expects to realize a 129 percent profit increase on its credit card portfolio with the solution.
“In today’s world, consumers have more options and a lot is at stake when it comes to capturing greater market share,” said Nikhil Behl, chief marketing officer at FICO† “Akbank has shown how a lender can build on its analytical capabilities with optimization to increase credit profits.”
Akbank’s core business is banking, which consists of corporate and investment banking, commercial banking, SME banking, consumer banking, payment systems, treasury transactions and private banking, and international banking services. In addition to its conventional banking activities, the Bank also conducts insurance agencies through its branches, on behalf of Ak Insurance and AgeSA Life and Pensions A.Ş.
With a strong and extensive domestic distribution network of 716 branches with more than 12,000 employees, Akbank operates from its headquarters in Istanbul and 19 regional directorates across Turkey. In addition to providing branch services, the traditional delivery channel, Akbank also serves approximately 18 million customers through Akbank Internet, Akbank Mobile, the Call Center, approximately 5,000 ATMs and more than 600,000 POS terminals.
About the FICO® Decisions Awards
The FICO Decisions Awards recognize organizations that have achieved remarkable success with 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; project scale, depth and width; and innovative use of technology. The 2022 jury members are:
Sidhartha Dash, research director at Chartis
Paul Deall, main risk, mortgages at Westpac (previous winner)
Senthil Erulapan, director, product engineering for merchant, risk and collections at FIS
Armando Junior, general manager, risk and compliance at Dock (previous winner)
Sheila Leverone, chief marketing officer at eDriving (previous winner)
Sibulelo Ncamani, head of operational risk and governance at Absa Bank (previous winner)
Graham Rand, operational researcher and editor of Influence
Dinesh Suresh, head, digital builds for consumer-backed loans at OCBC Bank (previous winner)
FICO (NYSE: FICO) is the driving force behind decisions that help people and businesses around the world thrive. Founded in 1956 and based in Silicon Valley, the company is a pioneer in using predictive analytics and data science to improve operational decisions. FICO holds more than 200 US and foreign patents covering technologies that increase profitability, customer satisfaction and growth for companies in the financial services, manufacturing, telecommunications, healthcare, retail and many other sectors. Using FICO solutions, companies in more than 120 countries are doing everything from protecting 2.6 billion payment cards from fraud, to helping people obtain credit, to making sure millions of planes and rental cars are on the right track. be in the right place at the right time.
More information on www.fico.com†
FICO is a registered trademark of Fair Isaac Corporation in the US and other countries.
Check out the source version at businesswire.com: https://www.businesswire.com/news/home/20220621005032/en/
FICO UK PR Team
Wendy Harrison/Parm Heer/Matthew Enderby
0208 977 9132