Data Mining: Five Myths of Data Mining

Many successful companies have discovered that myths which have

grown around data mining are just that, myths. Rather than falling victim to

them, visionaries have gleaned enormous competitive advantage by using data

mining for solving complex business problems and reach profitability.

As telcos look for additional business edge that will drive ARPU

and increase profitability and efficiency, data mining and the turning of data

into actionable information is now being used more widely than ever. However,

there are still many advances to be made. Telcos are under increasing

competitive and regulatory pressure to offer better services at reduced cost.

Providing a better service does not just entail delivering optimal network

quality, it involves really understanding customers' needs and fulfilling them

with profitable services. Also, reduced costs do not just involve cutting

prices. In today's economic climate, price pressure often acts as the catalyst

for examining internal systems, processes and costs, and striving for

operational excellence. Providing a better, more profitable service and

attaining operational excellence are two corporate goals the data mining

technology is well aligned with.

In fact, it was sophisticated data mining technology that

convinced rural Wal-Marts to stock up on a special version of Spam for the

hunting season. Go ahead. Laugh. But Spamouflage-Spam in camouflage cans has

been a huge success. Much more than a cute idea, Spamouflage has helped Wal-Mart

generate additional revenue from its existing customers and is emblematic of

just how deeply Wal-Mart understands the people it serves.

What is Data Mining Anyway?



Data mining is a powerful analytical tool that enables business executives
to advance from describing historical customer behavior to predicting the

future. It finds patterns that unlock mysteries of customer behavior. These

findings can be used to increase revenue, reduce expenses and identify business

opportunities, offering new competitive advantages.

Part of the reason why myths have developed around data mining

is because people are confused about what it is. At its core, data mining is

defined as a set of complex mathematical techniques used to discover and

interpret unknown patterns in detailed data. From the mid-1980s, when data

mining expanded from being applied in the field of academic, medical and

scientific research, it has been very effectively put to use in

telecommunications, retail, banking, insurance, and travel and hospitality.

Since data mining is considered an analytical tool, it is often

confused with online analytic processing (OLAP). OLAP is a valuable analytical

technique when used to analyze business operations to gain a historical

perspective on what has happened.

Data mining tackles a different class of problems. It can be

used to predict future events like sales in the next month based on promotions

or which type of customer is most likely to respond to a promotion.

The way a number of companies are already using it dispels the

five key myths about data mining.

Myth #1: Data Mining Provides

Instant Crystal Ball Predictions



Data mining is neither a crystal ball nor a technology where answers
magically appear after pushing a single button. It is a multi-step process that

includes defining the business problem, exploring and conditioning data,

developing a model, and deploying the knowledge gained. Data mining is all about

the data-successful data mining requires data that accurately reflects the

business.

In the telecommunications industry, operators must understand

where the power of data mining lies-in tackling specific business challenges

that are predictive or descriptive in nature.

These might include:

• Segmenting customers

• Predicting customers' propensity to buy (or to churn)

• Detecting fraud

• Increasing organizational efficiency

Telcos that understand the process are seeing real results. A

European mobile operator knows the value of its customers. Not just the

revenues, but the value. Both revenues and costs are calculated for each

customer, so marketing and CRM programs are developed based on the profitability

of customers. A South American telecommunications firm anticipates and prevents

the loss of high-value customers by identifying patterns that lead to customer

attrition by analyzing usage, services purchased and service-quality ratings.

Another European mobile operator used data mining to analyze churn patterns

leading to targeted proactive measures that identified customers and segments

with the highest propensity to churn. Based on this information, the operator

offered targeted marketing campaigns that led to a 50% reduction in churn in

target segments. Coupled with this, they realized a 30% take up rate on the

marketing campaign, further increasing customer satisfaction and customer

lifetime value.

Data mining can do much more than analyze customer behavior. A

leading operator in the US uses data mining to improve network performance,

without having to spend millions of dollars upgrading existing network

infrastructure. By continuous monitoring of performance rules, analyzing the

history of component and trunk usage, combined with current metrics from network

activity, this operator is able to ensure that calls are routed using available

capacity.

Myth #2: Data Mining is not yet

Viable for Business Applications



Data mining is a viable technology and highly prized for its business
results. The myth tends to be perpetrated by those who need to explain why they

are not yet using the process and revolves around two related statements. The

first says, "Huge databases can't be mined effectively," and the

second, "Data mining can't be done in the data warehouse engine."

Both statements were once true; it was also once true that airplanes couldn't

get off the ground.

Let's deal with these two statements together. Because today's

databases are so large, companies are concerned that the extra IT architecture

needed for data mining projects will add enormous costs, and the processing for

each project will take too long. But some of today's databases use parallel

technology, which enables in-database mining.

Myth #3: Data Mining Requires

Separate, Dedicated Database



Data mining vendors typically claim you need an expensive, dedicated
database, data mart or analytic server to mine data because of the need to pull

it into a proprietary format for efficient processing. These data marts are not

only costly to purchase and maintain, but also imply data extraction for each

separate data mining project, an expensive and time-wasting process.

Advances in database technology now demand that data mining is

no longer done in a separate data mart. In fact, effective data mining requires

an enterprise-wide data warehouse, which for the total cost of investment is

considerably less expensive than employing separate data marts.

Here's why. As companies implement data mining projects across

the enterprise, the number of users leveraging the data mining models continues

to grow as does the need to access large data infrastructures. A cutting edge

enterprise data warehouse not only efficiently stores all enterprise data and

eliminates the need for most other data marts or warehouses, but it also

provides an ideal foundation for data mining projects. That foundation is a

single enterprise-wide repository of data, which provides a consistent view of

the customer. By incorporating data mining extensions within the data warehouse,

companies can reduce costs in two additional ways. First, there is no need to

purchase and maintain additional hardware dedicated solely to data mining. And,

second, companies minimize the need to move data in and out of the warehouse for

data mining projects.

Myth #4: Only PhDs can do Data

Mining



Some consider data mining to be so complex that it must take at least three
PhDs to make it happen: one in statistics or quantitative methods, one in

business who understands the customer, and the other in computer science.

The truth is that successful projects have been completed with

nary a PhD in sight. For example, a South American telecommunications company

successfully tracked customer behavior changes that helped the company retain

98% of its high value customers during deregulation.

Data mining is a collaborative effort among knowledgeable

personnel in all three areas. People in businesses must guide the project by

creating a set of specific business questions and then interpret patterns that

emerge. Analytic modelers with an understanding of data mining techniques,

statistics, and tools must build a reliable model. IT personnel provide insight

into processing and understanding the data as well as providing key technical

support.

Myth #5: Data Mining is for Large

Companies with Lots of Customer Data



The plain fact is that if a company, large or small, has data that
accurately reflects the business or its customers, it can build models against

data that lend insights into important business challenges. The amount of

customer data a company possesses has never been the issue.

For example, a mid-sized mobile operator in the Asia Pacific had

an issue with fraud. The company used a centralized database to increase the

speed at which it could analyze CDRs (Call Detail Records) and better understand

the behavior of its customer base. As a result, detection of subscription and

usage fraud went from months to days and the operator saw a 60% reduction in per

account fraud loss. In times when operators are under increasing pressure to

increase the number of subscribers and ARPU, the ability to add significant

contribution to the bottom line without adding new subscribers or increasing

ARPU, had a major impact on the financial performance of this operator. Although

the database had been purchased to specifically deal with the fraud problem, the

operator soon realized many other benefits.

Savings through IT operations and system integration led to

shorter application development cycles by leveraging data from the data

warehouse resulting in 30-50% cost reduction. Once these gains had been seen,

the database was used by more and more departments enabling fast access to

critical business information for rapid decision making on areas such as churn,

daily activations and revenue streams. Users found that information, which

previously took months or weeks to access, was now available daily.

Seize the Day



Here's the bottom line: Data mining is no longer slow or expensive or too
complicated to work. The technology and the business know-how exist to put in

place an efficient cost-effective process. Telcos of various sizes are among

those putting the old myths to the test and proving that data mining is

essential to thrive in today's hotly competitive, customer-focused business

world.

Dennis Samuel,

VP, South East Asia & India Teradata, a division of NCR



vadmail@cybermedia.co.in