Customer Success Stories

DICTAPHONE SELECTS VIRTUAL GOLD TO POWER BUSINESS ANALYTICS FOR CONTACT CENTERS

In partnering with Virtual Gold, Inc., Dictaphone Corporation created a data mining component for its da Vinci quality monitoring system for contact centers, Dictaphone Corporation is teaming with a visionary pioneer in the field of application-specific data mining.

For Dictaphone, it was Virtual Gold's unique ability to apply next generation data mining to diverse contact center scenarios quickly and efficiently that made it the logical choice for the da Vinci data mining project. Other key advantages to the Virtual Gold approach are: the ability to link to call recordings that may illustrate potential problems; an easy-to-use interface that lets contact-center managers ask "what if?" questions of their center data; and accessibility through any Java-enabled web browser.

Virtual Gold takes data mining to the next level. The application lets the contact center and corporate manager analyze critical business data, in a unique fashion that leads to more accurate decision-making. It enables them to analyze contact center data using web-based charts, reports and querying applications that are all linked automatically to an intuitive data mining feature for discovering hidden patterns. Thus, data mining becomes an essential part of mainstream decision making as opposed to a separate, back-office analysis process.

By automatically finding actionable patterns that can impact the operation of the call center and customer relationships, Dictaphone is able to provide its customers a unique solution. It provides an enterprise-wide capability to discover such patterns and call them to the attention of managers instantaneously just when it matters most, namely, at the time of performing a query or accessing a report prior to making a business decision.

[top of this page]

IBM in partnership with Virtual Gold helps NBA coaches score big with IBM data mining application

When the Orlando Magic were devastated in the first two games of the 1997 National Basketball Association (NBA) Finals against the second-seed Miami Heat, the team's fans began to hang their heads in shame. But fortunately, the Magic had another trick up their sleeve. A data mining application developed by IBM and IBM Business Partner Virtual Gold uncovered a secret buried beneath the layers of statistics collected at every game.

The application, Advanced Scout, is specifically tailored for NBA coaches and statisticians. Advanced Scout showed the Orlando Magic coaches something that none of them had previously recognized. When Brian Shaw and Darrell Armstrong, were in the game, something was sparked within their teammate Penny Hardaway--the Magic's leading scorer at that time. Armstrong received more play-time and hence, Hardaway was far more effective. The Magic went on to win the next two games and nearly caused the upset of the year. Fans everywhere rallied around the team and naysayers quickly replaced their doubts with season ticket purchases for the following year.

Coaches, like business executives, carefully study data to enhance their natural intuition when making strategic decisions. But unlike business, the direct results of coaching decisions are played out under the eyes of millions of fans, and wrong calls can turn a team's fans against it--leading to lower ticket sales and possibly a vacancy in the head coaching position.

Before Advanced Scout, some teams, such as the Orlando Magic, began developing business intelligence software to find patterns in the piles of game data that the coaching staff collected during play. But with an average of 200 possessions a game and about 1,200 games a year, the sheer volume of statistics was overwhelming, and the applications produced only basic results--the kind of stats anyone could find in a local newspaper.

Data Mining for non-technical applications In 1993, Dr. Inderpal Bhandari, now CEO and founder of Hartsdale, New York-based Virtual Gold, was working at the IBM Watson Research Center in New York developing complex data mining applications that analyzed the quality of IBM software. Dr. Bhandari had the idea that, although data mining had traditionally belonged to the domain of high-level information technology, the same concepts could be applied to any non-technical scenario where large collections of data are present--for example, professional sports.

Being a long-time NBA sponsor, IBM approached the association with the idea of creating a data mining application.

The result was Advanced Scout, a data mining application that now uses IBM DB2 Universal Database, IBM DB2 Intelligent Miner and Virtual Gold's VirtualMiner software. About 25 teams are currently using Advanced Scout with great success. Says Tom Sterner, assistant coach of the Orlando Magic, "By helping us make better decisions, Advanced Scout is playing a huge role in establishing incredible fan support and loyalty--that means millions of dollars in gate traffic, television sales and licensing."

"My goal was to prove that data mining concepts can be applied to non-technical arenas. By linking DB2 Universal Database and Intelligent Miner for data through the VirtualMiner software, we are able to do exactly this."
--Dr. Inderpal Bhandari, CEO, Virtual Gold

Another member of the coaching team

During the course of each game, members of the NBA's Game Stats program, which IBM assisted in developing, manually enter game statistics into IBM ThinkPads. This data is then uploaded to the Advanced Scout Web site at the IBM Hosting Center and stored in DB2 Universal Database for AIX running on an RS/6000 server. Coaches can log on to the Advanced Scout Web site before, during or after a game to download this public data and merge it with the private data that each team collects independently on its laptops or PCs.

Using the Advanced Scout software, coaches can drill down into a vast array of statistics and data and unearth comprehensible patterns that were previously hidden among seemingly unrelated stats. An upcoming version of Advanced Scout will use DB2 Intelligent Miner. Coaches can ask Advanced Scout which players are most effective in correlation with time and the opposing players. "We're able to get, in realtime, statistical evaluations that allow us to put in the very best players for specific points in the game," says Sterner. "This application really helps us understand the relationships among the combinations of players on the court. Advanced Scout is changing the way we coach our team--it's helping us make far more effective decisions."

Data collected by Advanced Scout is also stamped with a universal time code. This means that when an intriguing pattern is spotted by the coaching staff using Advanced Scout, they can get the exact moment in the game where it occurred and instantly cue this up on videotape. Says Sterner, "We used to spend weeks scouring the tapes, but now we can instantly pull up a key spot in the game that, before Advanced Scout, we probably wouldn't even have known to look for."

Along with being Orlando's assistant coach, Tom Sterner serves as co-chairman of the NBA technology committee and has held previous positions in the IT industry. Sterner is a firm advocate of Advanced Scout, and bases his stance, not only on his team's visible improvement, but also on previous experience with e-business technology. "I've worked with this kind of data management software before," he says. "The scalability of DB2 Universal Database impresses me every time I use Advanced Scout."

Not just for the lab anymore While coaches currently have a robust tool with them at courtside to optimize player line-up, Advanced Scout's functionality will soon be expanded to include analyzing the effectiveness of specific plays that teams have designed. Sterner notes, "Coaches are going to be able, right from courtside--and in realtime--to ask Advanced Scout which play will be the most effective relative to the time elapsed and the specific combinations of players on the court."

Advanced Scout is the first in a series of sports-related data mining applications that IBM and Virtual Gold will implement in the near future. "But this trend shouldn't stop at sports," says Dr. Bhandari. "Any area where there are large collections of data is game for data mining, as the algorithms don't care if you're looking at free throws, genotypes or bugs in your code. My goal was to prove that data mining concepts can be applied to non-technical arenas. By linking DB2 Universal Database and Intelligent Miner for data through the VirtualMiner software, we are able to do exactly this--namely, simplify while still leveraging the full analytical capability of the powerful algorithms in Intelligent Miner for Data."

[top of this page]