IBM Boosts Content Classification Software to Streamline Enterprise Content Management

Cloudmark Uses IBM Classification Module to Improve Customer Satisfaction.


ARMONK, NY.- IBM (NYSE: IBM) today announced new capabilities in its content classification software used to automatically categorize large volumes of enterprise information, making it easier to find, access and use in the context of enterprise content management systems.

With its service-oriented architecture-based capabilities, the IBM Classification Module provides seamless connection to the IBM FileNet P8 content management platform to tackle the categorization of vast amounts of unstructured content in the enterprise, especially content stored or arriving in FileNet repositories. It automates the process of determining whether content is important, and how it should be handled. It can also automatically classify vast amounts of previously unmanaged content or reclassify content already under management so it can be easily leveraged for business purposes such as records management.

The IBM Classification Module helps empower users to determine the right level of automation for their business scenario, providing the right balance between automation and oversight through its configurable confidence levels and workflows designed within the classification review interface. This review capability uses the IBM Classification Module’s unique real-time learning to provide the system with feedback in order to improve accuracy and automatically adapt to changes inevitable in any business environment.

IBM also announced today that Cloudmark, a global leader in carrier-grade messaging security, has selected IBM content classification software to support its growing customer base with improved online customer support. The IBM software is helping Cloudmark reduce the workload and cost of handling online customer queries.

Cloudmark provides comprehensive anti-spam, anti-phishing and anti-virus solutions for Internet service providers, mobile operators, enterprises and consumers. Faced with a growing number of e-mail requests from customers, in excess of 500 per day, Cloudmark discovered that redundant questions and complex issues were taxing their call center. The company was eager to deliver faster responses to customer e-mails so fewer requests would come into their call center. Rather than adding temporary staff, Cloudmark selected IBM Classification Module to help identify recurring customer issues and concerns, determine which ones were most important, and how they should be handled.

“Our customers ask complex questions requiring specific information. The IBM Classification Module helps them get to the right answers more quickly,” said Kris Politopoulos, director, customer support, Cloudmark. “Using the IBM Classification Module, we achieve more than 90 percent accuracy in our automated responses. As a result, we have cut the number of tickets we receive in half and we can effectively support more products without adding support staff. Without the IBM Classification Module, we would have needed to double the size of our team to handle our growing customer base, which would have cost hundreds of thousands of dollars each year.”

IBM’s content discovery software understands the intent associated with a customer’s online question and suggests a solution that addresses their intent, allowing them to accept or decline the response or escalate to an agent in the contact center. The software gains knowledge and “learns,” both from existing e-mail history and from each response, thereby providing Cloudmark customers with the most relevant and up-to-date solutions to any given question.

By using the IBM software, Cloudmark’s call center e-mail deflection rate went from zero to 35 percent in the first week of implementation, meaning that 35 percent of inquiries that previously would have required handling by a call center representative were now reaching an online resolution. Not only did Cloudmark’s investment in the IBM solution pay for itself in less than three months, customer retention increased by 15 percent. Moreover, ultimately 40 percent of customer e-mails were handled via auto-response.

IBM Classification Module

With the ability to understand linguistics, semantics and the context of information, IBM Classification Module effectively analyzes unstructured and semi-structured content and metadata, allowing previously untapped information to be quickly and precisely classified so it can be more effectively found and reused. The content can even be classified within existing taxonomies, and the system can propose new taxonomies, making content easier to manage and retrieve and reducing the need for manual categorization.

IBM Classification Module is currently available from IBM and IBM Business Partners.
Contact(s) information

Holli Haswell
IBM Media Relations
512-286-3265
hhaswell@us.ibm.com