Published on 19-Dec-2010
"Using IBM SPSS Statistics and IBM SPSS Modeler, we have improved customer retention by 7 percent, with 54 percent of Fiat customers now replacing their existing cars with another Fiat brand." - Giovanni Lux, customer database & business intelligence manager, Customer Experience Management, Fiat Group Automobiles
Fiat Group Automobiles
BA - Business Analytics, BA - Business Intelligence, Big Data & Analytics
Auto sales fuel the company’s growth, daily operations, research and development and expanding global presence– in short, they underpin Fiat’s success in today’s highly competitive and volatile automotive marketplace. Knowing who is likely to purchase an automobile provides a huge competitive advantage, and this is precisely the information that IBM SPSS Statistics and IBM SPSS Modeler put at Fiat dealers’ fingertips.
Fiat Group Automobiles needed to determine the likelihood that future and returning customers would buy specific brands and models of Fiat cars, so that individual dealers could optimize the use of available marketing funds. The company also needed to better understand customer experience with dealerships and repair facilities.
Deploy IBM® SPSS® Statistics and IBM® SPSS® Modeler – complemented by IBM SPSS Collaboration and Deployment Services – to analyze data and create models to help predict customer behavior and enhance customer relationships.
-- Improved customer response rate to marketing initiatives by 15-20 percent. -- Improved customer loyalty by 7 percent. -- Supports continuous improvement of dealerships and repair facilities. -- Centralized analytical reporting and modeling system enhances productivity and lowers costs. -- Efficiently works with large Oracle database containing history on 64 million customers.
Fiat Group Automobiles designs, produces and sells vehicles under the
Fiat, Alfa Romeo, Lancia, Fiat Professional, Abarth and Jeep brands. Sells is
the operative word here. Auto sales fuel the company’s growth, daily
operations, research and development and expanding global presence–
in short, they underpin Fiat’s success in today’s highly competitive and
volatile automotive marketplace. Knowing who is likely to purchase an
automobile provides a huge competitive advantage, and this is precisely
the information that IBM SPSS Statistics and IBM SPSS Modeler put
at Fiat dealers’ fingertips.
Within the Customer Services organization, Customer Experience
Management is the keeper of IBM SPSS solutions at Fiat. “We use
predictive analytics and statistics to support two main goals,” explains
Giovanni Lux, customer database & business intelligence manager. “The first
goal is obviously to help Fiat sell cars. IBM SPSS Statistics and IBM
SPSS Modeler help us identify specific targets in terms of existing and
potential Fiat automobile owners, making it possible for dealers to
allocate their marketing budgets in the most efficient manner. Secondly,
we survey customers who have either bought a new car or used a Fiat
repair shop. We then analyze this data with IBM SPSS Statistics to
provide valuable insight into the level of customer satisfaction with our
dealers and repair facilities.”
Effective use of marketing funds
The foundation of these valuable analytics is Fiat’s Customer Analysis
Relationship & Experience (CARE) database, which contains a
complete history on more than 64 million customers and another 64
million vehicles. This huge data repository is instrumented by multiple
data sources, both internal and external; in turn, CARE feeds a secondlevel
analytics database for use by Statistics and Modeler.
“We produce approximately 150 targets a month for the dealers,”
explains Lux. “For example, Alfa Romeo is launching the new Giulietta
model, and the dealers want to assess the interest of loyal Alfa Romeo
customers through phone calls and direct mailings. They want to invite
customers and prospects to visit their dealerships, but at the same time,
they do not want to waste marketing funds on invitations that might be
Lux continues: “By defining predictive models based on 10 to 15
variables – things like age, gender, geography, financial information,
after-sales experience and purchasing history – we can tell the dealers:
‘These are the 100 people in this geographical area who are very likely
to buy a new car, and this set of 100 people is somewhat less likely to
buy.’ The dealers can then decide how many people to contact and
which contact method to use, depending on their individual budgets.
IBM SPSS Statistics and IBM SPSS Modeler make this critical
Fiat also depends on IBM® SPSS® Collaboration and Deployment
Services to automate these predictive models for more reliable results
and to ensure that the right people get the information they need to
take timely, appropriate action. And by centralizing analytical reporting
and modeling, Fiat enhances user productivity and lowers costs.
Similar segmentation is performed at the brand level, effectively
predicting the probability of selling small, medium and large vehicles.
“A dealer might simply want people to come into the dealership,
regardless of which car they buy,” notes Lux. “Or the dealer might say:
‘I have to sell a certain number of Cinquecento vehicles.’ The target
segmentation varies depending on whether we focus on the dealer or
the brand.” The predictive models are refreshed on a monthly basis
with new data to maintain their accuracy.
Prior to implementing Statistics and Modeler, Fiat supported the
dealers through one-to-one marketing initiatives using a competitor's
software. However, Fiat discovered that IBM SPSS solutions
would do an excellent job with a much lower total cost of ownership.
The company subsequently switched to providers to strengthen its
interconnected data management system.
In fact, the new predictive analytics and scoring models have exceeded
Fiat’s expectations. Says Lux: “Using IBM SPSS Statistics and IBM
SPSS Modeler, we have improved customer retention by 7 percent,
with 54 percent of Fiat customers now replacing their existing cars with
another Fiat brand. In addition, we have seen an increase of 15 to 20
percent in the response rate to marketing campaigns–a clear indication
that the IBM SPSS solutions are helping us target our potential
customer base more accurately.”
Are you happy?
On the customer intelligence side, Lux and his team conduct high-level
surveys – approximately 200,000 a year in Europe – to assess
satisfaction with both dealer and repair shop performance. The main
question is: “How strongly would you recommend the dealer (or repair
facility) that you used?”
Depending on the answer, Customer Experience Management seeks to
understand what the customer appreciated most about the experience
or, conversely, why the customer was dissatisfied. This data is analyzed
using IBM SPSS Statistics to better understand the characteristics of
both the promoters and the detractors, and the results are provided to
the dealers and repair shops. “We give them a monthly report
summarizing all the results, and they also get the free text replies from
the customer interviews,” says Lux. “This intelligence helps them make
improvements where necessary.”
Using Statistics and Modeler, Fiat is better able to determine the
likelihood that a customer will purchase a specific brand and model,
and the related timing of the purchase – and it can efficiently analyze
and report on customer service and warranty issues. “The ability to
predict customer behavior and enhance customer relationships is
absolutely critical to the success of Fiat Group Automobiles,” concludes
Lux. “At the end of the day, IBM SPSS Statistics and IBM SPSS
Modeler help us sell cars – and that’s what keeps the wheels turning at
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.
Products and services used
© 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.