How an international transportation company optimized high volume email processing in customer centers

Challenges

• The company was confronted with a high volume of incoming emails (between 100,000 and 250,000 customer emails daily), only 50% of which actually required a response
• Customer centers spent a significant amount of time sorting out emails that did not require action (e.g. out of office messages, FYI mails, etc.)
• The task was further complicated through the use of multiple languages in the emails

Solution

In partnership with PwC Germany, Cortical.io developed a Web service to detect emails that are not business case relevant.

This solution:

• flags irrelevant emails as “no case”
• categorizes the email topic (e.g. “invoice”) for proper routing
• was trained with a small amount of annotated emails and reference material related to the logistics domain (books, pdfs, websites, emails)
• uses language detection algorithms to route the emails to native language speakers
• can easily be adapted to new situations at short notice
• has minimal hardware requirements

The Cortical.io Difference

• SemanticPro combines human-level accuracy with fast processing (less than one second average response time) and high scalability
• The system is so precise that it detects errors done by human annotators in the training set
• The solution offers an “audit-track”–every single decision of the system can be clearly traced and each semantic processing step can be inspected, allowing the company to understand why each email has been classified as “case” or “no case”