Data Analytics in

Consumer Finance
Industry

Vineet Hemrajani

The author is with SBI GE Cards

Use of Data Analytics in Consumer Finance Companies

What is Data Analytics? Broadly speaking, data analytics can be described as the process of
collecting, analyzing and using data (related to demographic information, past behavior trends
etc.) to better understand and predict behavior of existing and prospective customers for business
decision making.

The common tools used to conduct data analytics range from simple cross tabulations and
segmentation analysis to more sophisticated statistical methods like multivariate & logistic
regression, discriminant analysis and cluster analysis. In the last few years optimization tools and
machine learning algorithms like neural networks and genetic algorithms have also been used to
perform advanced data analysis.

The recent years have seen increased use of data analytics in driving business strategies across
various industries. While the data analytics methods have been extensively used in FMCG,
Pharma and Telecom companies, their mainstay has been the consumer finance industry.

The wide scale applications of predictive Data Analytics started almost four decades ago in the
form of credit scoring. These credit scoring models or scorecards were used to predict customer
defaults. Today the FICO Risk score is the benchmark for credit decisioning process in the U.S,
so much so that the 'Prime' and 'Sub Prime' markets are defined on the basis of this score. With
the exponential increase in computing power and application of information technology in
business processes, more and more data analytics techniques and statistical tools are now being
applied for Marketing, Risk Management, Pricing & NPI functions in the consumer finance
industry.

In India, its common for major banks and financial services companies to use Data Analytics to
better manage their Credit Card, Housing, Personal & Auto loan and Insurance portfolios.

So why are businesses increasingly adopting the use of data analytics in their day to day
working? Clearly because Data Analytics allows these firms to predict the behavior of existing
and potential customers. Empowered with this information, the firms are able to devise suitable
strategies to better manage their respective businesses.

On the Risk Management front, Data Analytics techniques can help a bank develop an approval
strategy for its mortgage and auto loan applicants and also help to determine the optimal lending
rate. The same techniques can help an insurance firm decide the premium for its policyholders.
The data analytics techniques have been extensively used in the credit card businesses to decide
on credit and cash line assignments and ongoing authorization and fraud detection activities.
Data analytics is also effectively used in managing the collections functions of the consumer
finance companies. Using statistical modeling, the companies are able to predict the likelihood of
contacting a customer and chances of receiving a payment from him. This information is helpful
in choosing the right collections strategies that optimize collection efficiency and effectiveness.

On the marketing side of things, the use of data analytics in the form of response models helps
companies design and execute suitable cross sell, up sell, deep sell and retention strategies. In
the long run, creative use of past customer data through predictive modeling helps companies in
building powerful and effective analytical CRM platforms. These analytical CRM platforms allow
firms to make suitable offers to its customers and optimize campaigns through email, direct mail,
telemarketing and inbound call channels. Consumer finance companies in the United States,
where the credit bureaus are fairly developed, use data analytics to evaluate the quality of
consumer loan and insurance portfolios during mergers, acquisitions and securitization deals.

Now that we know what the benefits from data analytics are, the next question is what do
companies need to do to effectively use data analytics. Experts in this field believe that to reap

2
 Data Analytics in Consumer Finance Industry

the maximum benefits from data analytics, firms have to invest in the right technology, hire the
right people and last but not the least develop standardized and robust processes of data
collection, data retrieval, data analysis and strategy implementation. For example a company may
invest in a separate analytics datamart to capture the relevant customer data. This data is mainly
of three types: demographic, behavioral and contact information. While demographic data refers
to information about customer characteristics like age, income etc., behavioral data includes
information of customer’s prior performance like response to past campaigns, transaction history
and delinquency behavior. Contact information includes history of prior offers and contacts made
to the customer.

Once the data mart is ready, the company needs to build efficient and robust systems for
extracting and analyzing data from the data mart. After the required data analysis is completed
and a suitable strategy using data analytics has been devised, it is important to ensure that
strategies are implemented efficiently and accurately. The implementation of analytically driven
strategies has been rather ‘painful’ process for most companies. However if the right IT
infrastructure exists and process planning is rigorous then implementation can be accomplished
with minimal disruption of business processes and with limited impact on the company’s existing
systems and resources. To facilitate easier and faster implementation, softwares that integrate
with a company’s work flow and account receivable systems to implement the risk and marketing
strategies are now available. Campaign management packages, systems that enable easy
execution and tracking of analytically driven targeted marketing campaigns are also being
increasingly used by consumer finance companies.

After a particular business strategy (a new risk policy or marketing campaign) has been
implemented, the companies need to measure the performance of the business strategy and
make sure that the results can be tracked effectively for future use. The process of continuous
designing, executing, and tracking allows companies to ‘test and learn’ about consumer behavior
and optimal offer selections and thereby helps them gain a competitive edge.

The above process requires firms to make investments in technology- Database packages,
Statistical Software, implementation platforms and reporting & analysis tools. Most of the major
software companies have developed data mining and analytics softwares, however the use of
specialized statistical software for predictive modeling and of reporting and analysis tools is
common. In addition to the IT infrastructure, the companies need to hire the right people. A team
of systems specialists and data analysts is required to develop and maintain efficient datamarts
and robust implementation & analysis systems. To conduct data analytics, teams of econometric
& statistical modelers and business analysts that can effectively perform strategic analysis and
build predictive models need to be developed.

Major financial services firms in India have built internal data analytics and business intelligence
teams of data analysts and statistical modelers that support marketing and risk management
activities. A few independent third party data analytics companies that provide end to end data
analytics solutions supporting consumer finance companies in India have also grown to a
significant size in the last few years.

The market for consumer finance products is growing at a rapid rate in India. To seize this
opportunity, new financial services firms are entering the industry and the existing banks are
increasingly focussing on retail portfolios. The pressures to make high profits remain high in the
face of increasing competition. For consumer finance companies, use of data analytics is no more
a luxury but a necessity. Firms that invest in data analytics now will reap in the benefits for a long
time to come.