Technology Serves as a Watchdog for Call Quality

While most companies record some customer support calls, in the past, these calls haven’t been used for much. If they record a few calls, they’re probably being used for agent evaluation. If they record all their calls, they’re probably storing them only because the law requires them to, or they want a call record in case a dispute arises later. Few companies today are recording all their calls and mining them for intelligence.

Yet recorded calls contain so much potentially useful data, companies looking to improve the customer experience are ignoring a gold mine. In the past, it simply wasn’t possible to listen to all these calls, since it required a human being to do it manually. Technology has changed all that, according to Bernard Marr writing for Forbes. In particular, the convergence of several technologies, not least among them analytics, is enabling companies to use recorded calls as a valuable source of information.

“With the advent of natural language processing (NLP) technologies and the ability to understand more unstructured data, like phone call recordings, companies are sitting on a wealth of information every time they record a call,” he wrote. “And because the field is expanding so rapidly, there are many different ways companies can put this data to use.”

NLP is far more than “speech recognition.” The technology to understand what people say on the telephone isn’t new, but today, NLP can analyze tone, vocabulary, word choice, sentiment and more, and actually gauge the caller’s mood, intentions and even demographic. (Some NLP solutions can determine a caller’s age pretty successfully, for example.) This is valuable information for a company to have, because it might dictate which agents you route the call to, which increases the chances that the customer will have a positive experience. You may have agents who specialize in calming angry customers, for example, or those who are extra-patient with elderly callers.

Analytics can boost NLP technology immensely by helping companies choose the best route of action for a call and extracting customer sentiment (either individually or en masse) from recorded calls.

“The predictive models can provide insights on the best ways to handle different types of calls, in order to boost an agent’s effectiveness and improve the customer’s experience on the call,” wrote Marr.

Some solutions even bring social media into the mix, combining the intelligence extracted from calls with customers’ social media activity to even better predict the customers’ needs and intents. Combining these technologies with an outside service to monitor quality, such as third-party call monitoring, and companies are well-placed to be able to understand precisely what kind of customer experience they are offering, how customers are responding to it and how they can improve.

While improving self-service technologies help take some of the onus off the contact center – nowadays, people pick up the phone only as a last resort – this means that the calls that find their way to your contact center are extra-important and likely quite complex. It’s at these moments that customer experiences are made or broken. Under these circumstances, ignoring quality is a foolish mistake. 

Edited by Alicia Young

Share this Page