Published on 04-Mar-2011
Validated on 03 Jun 2013
"It would have been possible to obtain the analytical models from other vendors and complete the analysis, but it would not be feasible to deploy or maintain a project such as ours without IBM SPSS Modeler’s straightforward stream structure." - Kadir Karakurum, CRM Manager, Fortis Turkey
Business Analytics, Business Intelligence
Fortis is an international financial services provider engaged in banking and insurance. The company offers personal, business and institutional customers a comprehensive package of products and services through its own channels, in collaboration with intermediaries and through other distribution partners. With a market capitalization of €31 billion, Fortis ranks among the 20 largest financial institutions in Europe.
After financial services provider Fortis purchased Disbank, a large Turkish bank, it needed to rebrand its banking operations there with an emphasis on customer growth and satisfaction. But to accomplish that, Fortis Turkey required an in-depth understanding of its new customers and which products and services those customers would most desire.
Using IBM SPSS Modeler, Fortis Turkey was able to identify which products or services were most likely to be accepted by more than 1.7 million individual customers. This enabled the bank to successfully market investment products, loans, safety deposit boxes and other offerings to the precise customer segments that desired them.
Fortis Turkey’s CRM team prepared a multi-faceted project plan, creating a campaign called “Fortis Has an Offer for You.” For the core analytical work, Fortis turned to IBM SPSS Modeler. The company used the software’s powerful segmentation and best basket modeling capabilities to analyze existing data from a large marketing data warehouse.
The Fortis CRM Team used the software for: • Income estimation • Customer segmentation • "Best basket” modeling • "Next best product” selection for each customer • Daily production of the offer lists linked to online campaign management and showing usage of the lists within the channels
Fortis is an international financial services provider engaged in banking and insurance. The company offers personal, business and institutional customers a comprehensive package of products and services through its own channels, in collaboration with intermediaries and through other distribution partners. With a market capitalization of €31 billion, Fortis ranks among the 20 largest financial institutions in Europe. Its solvent position, presence in 44 countries and dedicated, professional workforce of 56,000 provides a combination of global strength and local flexibility – offering its clients optimum support.
Launching a successful brand in a new market
In line with its strategy to combine banking and insurance expertise in growth markets in Europe and Asia, Fortis acquired Disbank, Turkey’s seventh largest privately owned bank. Fortis tasked its retail customer relationship management (CRM) team to prepare Fortis Turkey for the launch campaign, aiming to take advantage of the many leads the bank anticipated.
To be successful, Fortis Turkey needed to be able to offer the “next best product” to each customer through its branches, Internet banking and Contact Center channels. Aside from being a challenging task, this was complicated by a strict time limit due to many parallel projects. Fortis Turkey’s CRM team prepared a multi-faceted project plan, creating a campaign called “Fortis Has an Offer for You.” For the core analytical work, Fortis turned to IBM SPSS Modeler. The company used the software’s powerful segmentation and best basket modeling capabilities to analyze existing data from a large marketing data warehouse.
Fortis upgraded the existing campaign management tool, which was developed in-house, so that it could make offers through inbound customer contacts regardless of touchpoint. The bank also designed an online process that provided bank personnel with daily evaluations and updates, ensuring all customer contact channels were synchronized to avoid overlaps.
Thanks to these efforts and the predictive modeling capabilities of IBM SPSS Modeler, Fortis Turkey was able to:
- Identify the “next best products” for more than 1,700,000 customers using segmentation and “best basket” studies
- Offer the product or service with the highest probability of acceptance by a specific customer contacting the bank through a branch, Internet banking, or the Contact Center
- Use each answer given by a customer to an offer or any change in the current product basket to prepare a new offer within one day
- In the first month, achieve an average 16 percent acceptance rate of offers for 16 different products such as investment products, loans and safety deposit boxes
- Save customer sales representatives time and effort now that they no longer have to estimate or guess what would be the best offer for a specific customer
Providing the “next best offer” through multiple channels
When Disbank was acquired, Fortis began re-branding studies immediately. The corporate communications department prepared a large kick-off campaign to introduce the Fortis brand to the Turkish market. The bank anticipated that such a campaign would attract a lot of attention, creating many sales opportunities.
It’s always been challenging to use customer-oriented contacts as sales opportunities. It’s even harder to convert a lead obtained from a communications effort such as mass advertising. Therefore, banks must take advantage of every sales opportunity in today’s competitive market. Customer sales representatives with a small customer portfolio may know each of their customers by name and be able to select a suitable product or service to offer their customers. These days, however, most representatives have portfolios with thousands of customers. The sales representative doesn’t have time to assess an individual customer’s needs. Offers are far from customized, and might likely be the first product or service on a list showing what the customer does not already have. To help representatives make the right offer to the right customer, centralized, multi-channel CRM capabilities are essential.
Previously, the Disbank CRM team had successfully prepared propensity-based sales campaigns. For some products, the acceptance rate was up to 90 percent. With the acquisition, however, Fortis Turkey had to predict the “next best product” for more than 1,700,000 customers – and be able to update the offers in short periods of time.
Applying the power of predictive modeling
The project plan for “Fortis Has an Offer for You” incorporated both analytical tasks and operational CRM capabilities. This enabled Fortis to deliver offers during inbound customer contacts through multiple channels. IBM SPSS Modeler’s powerful data mining and predictive modeling capabilities provided the foundation for the project. The Fortis CRM Team used the software for:
- Income estimation
- Customer segmentation
- “Best basket” modeling
- "Next best product” selection for each customer
- Daily production of the offer lists linked to online campaign management and showing usage of the lists within the channels
Each of these tasks could have been a separate project requiring a considerable amount of time and effort to accomplish. However, with IBM SPSS Modeler’s “completeness of vision,” Fortis completed all of the tasks in less than two-and-a-half months. Each customer offer was ready to be presented in all three channels on the day “Disbank” became “Fortis Turkey.”
Successful results in the first month
Within two months, Fortis made 91,603 offers to 61,442 customers who contacted the bank through the three channels. In the first month alone, the bank averaged a 16 percent acceptance rate of offers for 16 different products. In a project like this one, analytical capabilities are a must. The bank relied on algorithms such as K-means, TwoStep, Kohonen networks, Apriori and GRI. IBM SPSS Modeler provided not only these analytical capabilities, but was easy to use and offered a completeness of vision that no other product could match. Today, the bank’s offers are updated daily through IBM SPSS Modeler.
Kadir Karakurum, CRM manager of Fortis Turkey, said, “It would have been possible to obtain the analytical models from other vendors and complete the analysis, but it would not be feasible to deploy or maintain a project such as ours without IBM SPSS Modeler’s straightforward stream structure.”
Products and services used
IBM products and services that were used in this case study.
Software Services for Information Management
Footnotes and legal information
About IBM Business Analytics
IBM Business Analytics software delivers complete, consistent and
accurate information that decision-makers trust to improve business
performance. A comprehensive portfolio of business intelligence,
predictive analytics, financial performance and strategy management,
and analytic applications provides clear, immediate and actionable
insights into current performance and the ability to predict future
outcomes. Combined with rich industry solutions, proven practices and
professional services, organizations of every size can drive the highest
productivity, confidently automate decisions and deliver better results.
As part of this portfolio, IBM SPSS Predictive Analytics software helps
organizations predict future events and proactively act upon that
insight to drive better business outcomes. Commercial, government
and academic customers worldwide rely on IBM SPSS technology as a
competitive advantage in attracting, retaining and growing customers,
while reducing fraud and mitigating risk. By incorporating IBM SPSS
software into their daily operations, organizations become predictive
enterprises – able to direct and automate decisions to meet business
goals and achieve measurable competitive advantage. For further
information or to reach a representative visit www.ibm.com/spss.
© Copyright IBM Corporation 2010 IBM Corporation Route 100 Somers, NY 10589 US Government Users Restricted Rights - Use, duplication of disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Produced in the United States of America May 2010 All Rights Reserved IBM, the IBM logo, ibm.com, WebSphere, InfoSphere and Cognos are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol (® or TM), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml. SPSS is a trademark of SPSS, Inc., an IBM Company, registered in many jurisdictions worldwide. Other company, product or service names may be trademarks or service marks of others.