Predictive Analytics in Financial Services Industry

8/7/2019 Predictive Analytics in Financial Services Industry

http://slidepdf.com/reader/full/predictive-analytics-in-financial-services-industry 1/6

ANALYTICS IN FINANCIAL SERVICES INDUSTRY

In modern times, financial services is one of the most competitive and dynamic industry sectors.

The industry faces new challenges every day and though significant time and energy is spent

addressing today’s challenges, new issues threaten growth, profitability and investor

confidence/protection. To tackle the ever increasing challenges in the market place investments

in IT thus become a strategic choice for financial institutions. IDC projects that the financial

services industry will account for more than 20 percent of the $1.2 trillion spent worldwide on IT

between 2004 and 2008.

Financial institutions need to understand the growing role that customer analytics can play in

helping them target customers, reach and retain customers, streamline general operations, and

strengthen their distribution. Perhaps no technology has added to revenue and profitability

growth as much as predictive analytics.

UNDERSTANDING ANALYTICS

Analytics consists of a variety of mathematical techniques from statistics and data mining that

derive insight from current and historical data to make predictions about future events. Such

predictions rarely take the form of absolute statements, and are more likely to be expressed as

values that correspond to the odds of a particular event or behavior taking place in the future. In

business, predictive models exploit patterns found in historical and transactional data to identify

risks and opportunities. Models capture relationships among many factors to allow assessment

of risk or potential associated with a particular set of conditions, guiding decision making for

candidate transactions.

Credit Scoring, one of the most well‐known applications is used throughout financial services.

Scoring models process a customer’s credit history, loan application, customer data, etc., in

order to rank individuals by their likelihood of making future credit payments on time. Apart

from prediction, predictive analytics can provide information to identify new marketing

channels and other competitive advantage through cross selling by exploiting the hidden

relationship in the data assimilated. This model can also help companies to retain customers by

increasing customer activities as reaching to certain phase where their future behavior can be

predicted accurately.

SIDEBAR ANALYTICS AND BUSINESS INTELLIGENCE (BI) BI delivers insight whereas Analytics deliver action. Traditional business intelligence (BI) tools

extract relevant data in a structured way, aggregate it and present it in formats such as

dashboards and reports. BI tools are more exploratory than action‐oriented. BI helps businesses

understand business performance and trends.



Whereas BI focuses on past performance, analytics forecasts behavior and results in order to

guide specific decisions. If BI tells what’s happened, analytics tells what to do. Both are

important to making better business decisions. Analytics also focuses on distilling insight from

data, but its main purpose is to explicitly direct individual decisions. Many BI suites now include

some analytics, ranging from report‐driven analytics that synthesize past performance data to

predictive analytics used in forecasting.

APPLICATION OF PREDICTIVE ANALYTICS IN FINANCIAL SERVICES

Although analytics can be put to use in many applications, A few examples in financial services,

where analytics has shown positive impact in recent years are outlined below.

ANALYTICAL CUSTOMER RELATIONSHIP MANAGEMENT (CRM)

Analytical Customer Relationship Management is a frequently used commercial application of

Predictive Analysis. Here, predictive analysis techniques are applied to customer data to pursue

CRM objectives.

DIRECT MARKETING

Marketing department in a financial services organization is constantly faced with the challenge

of coping with the increasing number of competing and innovative products, varied consumer

preferences, and the availability of various methods/channels to interact with each consumer.

An effective marketing strategy involves understanding the amount of variability among various

consumer segments and customizing communication to these segments for greater profitability.

Analytics can help identify consumers with a higher likelihood of responding to a particular

marketing offer. Appropriate models can then be built using data from consumers’ past

purchasing history and past response rates for each channel. These models can be further

refined with additional information about the consumers demographic, geographic and other

characteristics. Targeting consumers based on the models can lead to substantial increase in

response rate and also reduces cost per acquisition. Apart from identifying prospects, analytics

can also help in ascertaining the most effective combination of products and marketing channels

that should be used to target a given consumer.

CROSS‐SELLING AND UP‐SELLING PRODUCTS AND SERVICES

Financial

services

organizations

often

collect

and

maintain

huge

amounts

of

data

(e.g.

customer

records, transaction records, etc). Exploiting hidden relationships in this data can provide a

competitive advantage. For an organization that offers multiple products, an analysis of existing

customer behavior can lead to effective cross selling of products (as in the insurance industry).

Predictive analytics can help analyze customers’ spending, usage and other behavior, and help

cross‐sell the right product at the right time leading to higher profitability and strengthening

customer relationships.



RETAINING EXISTING CUSTOMERS

Analytics can help financial services organizations retain existing customers. By understanding

the patterns associated with customer defections, marketing pricing cycles, and elasticities, they

can identify profitable customers who are most likely to leave, and take early action to keep

them,

before

it

is

too

late.

By

frequently

examining

a

customer’s

past

records,

spending,

and

other behavior patterns, predictive models can determine the likelihood of a customer wanting

to terminate service sometime in the near future.

UNDERWRITING

Financial services organizations have to account for risk exposure due to their varied services

and determine the cost needed to cover the risk. For example, auto insurance providers need to

accurately determine the amount of premium to charge to cover an automobile and driver. A

financial company or a bank needs to assess a borrower’s potential and ability to pay before

granting a loan. Predictive analytics can help underwriting of these services by predicting the

chances of loss, default, bankruptcy, etc. Predictive analytics can streamline the process of

customer acquisition, by predicting the future risk behavior of a customer using application level

data. Proper predictive analytics can lead to proper pricing decisions, which can help mitigate

future risk of default.

Many insurance companies use predictive modeling solutions to support underwriting work.

Predictive analytics helps in improving underwriting loss ratios and increases residual benefits as

a result of reduced expenses.

COLLECTION ANALYTICS

Every portfolio has a set of delinquent customers who do not make their payments on time. The

financial institution has to undertake collection activities on these customers to recover the

amounts due. A lot of collection resources are wasted on customers who are difficult or

impossible to recover or have gone bankrupt. Predictive analytics can help optimise the

allocation of collection resources by identifying the most effective collection agencies, contact

strategies, legal actions and other strategies for each customer, thus significantly increasing

recovery at the same time reducing collection costs.

FRAUD DETECTION

Fraud is a big problem for financial services organisations and can be of various types.

Inaccurate credit applications, fraudulent transactions, identity thefts and false insurance claims

are some examples. Fraud plagues firms all across the spectrum. Examples include credit card

issuers, insurance companies, retail merchants, manufacturers, business to business suppliers

and even services providers. Here predictive analytics is often used to help separate the “bads”

from the “goods” and reduce a business’s exposure to fraud.



ENHANCING DISTRIBUTION

As multiple channels become the need of the day, analytics can help companies understand the

selling methods and needs of specific channels, including wholesalers, brokers, direct selling

agents, and independent agents. This understanding will help firms develop strategies for each

channel,

and

create

solutions

and

tools

that

help

those

distributors

do

a

better

job

of

targeting

the right customers and selling products. At the same time, companies can also use analytics to

sift through large amounts of data to monitor distributor performance and identify the most

profitable distributors.

PREDICTIVE ANALYTICS IN INSURANCE

Source: Harnessing analytics for the insurance industry, Inductis ANALYTICAL MODELS

In

general

analytics

means

predictive

modeling,

scoring

of

predictive

models,

and

forecasting.

However, companies are increasingly using the term to describe related analytic fields, such as

descriptive modeling and decision modeling or optimization which involve rigorous data

analysis, and are widely used in business for segmentation and decision making with different

purposes.



PREDICTIVE MODELS

Predictive models analyze past performance to assess how likely is it for a customer to exhibit a

specific behavior in the future, in order to improve marketing effectiveness. The process consists

of models that seek subtle data patterns to answer questions about customer performance, for

e.g.,

fraud

detection

models.

Predictive

models

evaluate

the

risk

or

opportunity

of

a

given

customer or transaction, in order to arrive at a decision.

DESCRIPTIVE MODELS

Descriptive models “describe” relationships in the data to categorize customers or prospects

into groups. Unlike predictive models that focus on predicting a single customer behavior (such

as credit risk), descriptive models identify many different relationships between customers or

products. The descriptive models, however, do not rank customers by their likelihood of taking a

particular action the way predictive models do. Descriptive modeling tools can be utilised to

develop agent based models that can simulate large number of individual agents to predict

possible futures.

DECISION MODELS

Decision models describe the relationship between all the elements of a decision i.e., the known

data (including results of predictive models), the decision and the forecast results of the

decision, in order to predict the results of decisions involving many variables. These models can

be used in a data‐driven approach to improving decision logic that involves maximizing certain

outcomes while minimizing others (optimization). Decision models are generally used offline, to

develop decision logic or a set of business rules that will produce the desired action for every

customer or circumstance.

BENEFITS OF ANALYTICS

The benefits of using analytics in financial services organizations are manifold and include:

Analytics provides insight on future customer behavior that can help identify the best action

for every customer or transaction. Predictive analytics also facilitates other strategic action,

such as placing accounts at collection agencies that will maximize collected monies, or

detecting financial frauds, abuse and error in healthcare claims.

Analytics provides explanations for complex questions and processes transactions speedily

and accurately. Decisions that were long pending can be taken in seconds, right from

“instant” credit offers to insurance underwriting to real‐time fraud detection.

With analytic insight, businesses can more accurately measure business risks and reduce

losses. This includes losses due to fraud, since analytics can detect the abnormal patterns in

application, purchase, claims, transaction or network data.



Analytics operates consistently and dependably, relying on mathematical techniques. This is

critical to for controlling risk as required by regulators in banking, insurance and other

industries.

The end result of faster, smarter and more consistent decisions is a more agile business that

can respond quickly to market conditions, improve customer service and profitably grow

into new markets.

THE CHALLENGE AHEAD

There is clearly a benefit to applying predictive analytics to more areas of the financial services

organization. However, taking broader advantage of analytics can require significant effort. The

greatest challenge is working across traditional information silos to integrate and consolidate

data into a single, consistent format ‐ which is the foundation of sound analytics. In addition to

having the data warehousing and data mining capabilities to manage internal data sources,

companies will also need to leverage data from external sources, such as commercial providers

like Experian and Dun & Bradstreet, and government data sources.

Companies will also need to proactively address change management since implementing

predictive analytics solutions will likely create the need for new processes, skills, and roles. To

oversee these efforts, financial companies should consider designating a data specialist or a

‘business intelligence guru’ who is responsible for evaluating sources of information, and

ensuring the quality and integrity of enterprise data.

The importance of analytics will continue to grow. To remain competitive, financial services

organization will need to seize the opportunities presented by today’s analytical tools to

increase operational efficiency and gain the deeper insights that will allow them to work more

effectively with distributors and compete more successfully for customers.

Documents

Predictive Analytics in Financial Services Industry