About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Banca Alpi Marittime Credito Cooperativo Carrù S.c.p.A.
How a small, rural bank used AI to make happier customers and cut costs
To accelerate credit requests, Banca Alpi Marittime joined with IBM Business Partner Analytics Network S.r.l. to launch Credit Scorecard App, an AI-powered approval engine backed by IBM® SPSS® Modeler technology. Using advanced data modeling, the system evaluates applicants’ financial information, authorizing credit lines without human intervention.
With over one-third of its accounts requesting lines of credit each year, Banca Alpi Marittime Credito Cooperativo Carrù S.c.p.A. wanted to deploy a more efficient approval process.
The bank deployed Credit Scorecard Application by Analytics Network S.r.l., an AI-powered approvals platform that uses SPSS Modeler software to automate the process.
Results
vetted and approved without human intervention
can be reassigned to other tasks, saving several thousand euros each year
by providing bank patrons with answers more quickly
More than just numbers
Nestled among farmlands and vineyards, the municipality of Carrù lies upon the rolling plains of the Piedmont region of Italy. And on a small hill on the outskirts of the town stands a medieval castle, originally built sometime around AD 1000. This historic structure serves as the home of another longstanding institution for the region—Banca Alpi Marittime.
Founded at the end of the 19th century, the bank has served the surrounding community, providing financial services and support to the farmers, workers and families that call this region their home.
“We’re not a faceless corporate bank focused only on profit,” explains Piero Biagi, General Director at Banca Alpi Marittime. “We are a credito cooperativo [a cooperative credit bank], so our focus is to improve the economic life of our members and our region. We want to provide them with the credit and resources to live their lives, build their families and grow their businesses.”
In pursuit of this goal, the bank wanted to improve the level of support surrounding its credit line offerings, banking accounts that included personal lines of credit to consumers and businesses. At the time, bank managers would evaluate each credit request as it came in, attempting to make the right decision for the organization and its members with the information on hand. And for credit lines that already existed, these same personnel would need to evaluate existing credit limits each year to determine whether they should be renewed or adjusted.
“It took a lot of our time,” adds Biagi. “Over one-third of our customers require a credit line on their account, and I wanted something more efficient to do this job. I knew that the right technology could solve this problem, but we’re a small bank, and we don’t have IT resources, nor specific data science skills.”
In particular, Biagi was confident that a solution powered by AI could easily accelerate the decision-making process surrounding these critical accounts. But was there a way to bring this leading-edge technology to Carrù?
Small business, big technology
Luckily, Banca Alpi Marittime found IBM Business Partner Analytics Network, a company that specializes in democratizing AI. And working together, the two deployed a credit approval solution backed by machine learning and SPSS Modeler technology.
“Our Credit Scorecard application is now processing all of the credit renewals and requests for the bank that are under EUR 100,000,” clarifies Luca Camporese, Managing Partner and Founder of Analytics Network. “So let’s say 100 credit lines are going to expire tomorrow. The solution will evaluate them in a batch, studying the available intelligence—their credit scores, their history with the bank and any other records—to determine if they should be approved. About half of these requests are processed automatically, and the customers receive a notice through the bank’s mobile app.”
He continues: “But for the others, these are more complicated situations. Maybe it’s their first time asking for assistance. Maybe some strange behavior has happened with the account. If there is not enough information available, Credit Scorecard will notify the bank manager to help with the decision.”
The approval logic for the solution relies on algorithms and machine learning code developed by Analytics Network, while SPSS Modeler serves as the engine overseeing data modeling and analysis efforts. And to deliver the IBM technology within the Credit Scorecard framework, Analytics Network uses an IBM Embedded Solution Agreement (ESA).
“Often, AI is something that is hidden from the end user,” notes Camporese. “In a lot of ways, the customer is unaware of what we are doing in the background. And in some ways, they do not care. We are bringing the value of AI to the small business, and the ESA lets us worry about the integration, so the customer doesn’t have to.”
Better service, better savings, better banking
After deploying the new credit processing solution, Banca Alpi Marittime radically accelerated its approvals process, automatically resolving approximately 50% of the 6,000 requests it receives annually. In turn, this automation frees up roughly ten full-time equivalents that can be reassigned to other tasks—a savings of a few hundred thousand euros each year.
“We had a full return on our investment in just a few months,” adds Biagi. “And thanks to this application, we improved our clients’ experience and reduced our costs. We receive an automatic answer to requests that don’t need to wait for office hours.”
And the bank can remain confident that these credit decisions are being handled according to its business rules to reach an intelligent decision for patrons. “The Analytics Network team delivered a smart, data-driven solution,” continues Biagi. “And this project shows that you can innovate with data science without a large investment of time, money or skills.”
Further, Analytics Network continues to be pleased with its role as an IBM Business Partner and with the IBM technology used to power its solutions. “With SPSS Modeler, we were able to do everything—from data preparation to manipulation to modeling to deploying,” comments Camporese. “It’s a visual interface that is very easy for our data scientists to use. If we were to do this same work with R or Python, it would be a pain. We’d have to ask our customers to pay more just to maintain the solution, but with IBM, we can keep the TCO [total cost of ownership] low.”
Banca Alpi Marittime Credito Cooperativo Carrù S.c.p.A.
Founded in 1899 with the original name “Cassa Rurale di depositi e prestiti di Carrù,” Banca Alpi Marittime (link resides outside of ibm.com) is headquartered in an ancient medieval castle located in Carrù, Italy. The bank operates as a credito cooperativo [a cooperative credit bank] with a key focus on local economic development.
Currently, Banca Alpi Marittime operates through 21 branch locations, supporting 95 municipalities in the provinces of Turin, Cuneo and Savona.
About Analytics Network S.r.l.
IBM Business Partner Analytics Network (link resides outside of ibm.com) delivers cognitive solutions for machine-driven decision making. The company was founded in 2016 and is headquartered in Bologna, Italy.
Legal
© Copyright IBM Corporation 2020. IBM Corporation, IBM Hybrid Cloud, New Orchard Road, Armonk, NY 10504
Produced in the United States of America, September 2020.
IBM, the IBM logo, ibm.com, and SPSS are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at ibm.com/trademark.
The content in this document (including currency OR pricing references which exclude applicable taxes) is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates.
The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.
