Zendesk tool taps machine learning to nip customer-service problems in the bud

Each ticket gets a score predicting its likely outcome

Machine learning has been making its way into a growing range of enterprise software in recent months, and on Wednesday Zendesk provided a fresh example: Satisfaction Prediction, a new tool designed to help companies catch potential customer-service problems before they happen.

Essentially, Satisfaction Prediction learns from historical customer-interaction data and uses that knowledge to predict which current customer-service interactions are likely to run into trouble.

The tool's knowledge base draws from an analysis of factors in past interactions that can precede customer dissatisfaction -- the amount of effort involved to solve a ticket, for example, and the language used -- along with the customer’s ultimate satisfaction rating at the time.

Then, as new customer service tickets arise, it analyzes the new customer signals against that knowledge to generate a score for each predicting the likely outcome. Armed with that information, agents and managers can escalate conversations at risk of a negative result, for example.

A type of artificial intelligence, machine learning is No. 5 on Gartner's recently published list of the top 10 technology trends that will be strategic for most organizations in 2016.

"The trend that I am seeing is that more organizations are starting to operationalize their analytics," said Fern Halper, director of TDWI Research for advanced analytics. "They are making it part of a business process."

Several factors are driving this trend, Halper said.

First, "organizations want 'right-time' or real-time analytics so they can make better timely decisions and become more competitive," she explained. "They are beginning to see data and analytics as a way to improve business processes and drive operational efficiencies."

Analytics can also lead to revenue growth, she noted.

As the volume and frequency of data increases, meanwhile, it's also often not even possible to perform analytics and make decisions manually, necessitating a more automated approach, she said.

In general, predictive analytics is becoming more mainstream, Halper said, but fewer than 20 percent of the respondents she surveyed recently were at the point of embedding models into business processes.

Satisfaction Prediction is now available in limited beta, with general availability planned for next year. Pricing details were not available.

Join the Good Gear Guide newsletter!

Error: Please check your email address.

Our Back to Business guide highlights the best products for you to boost your productivity at home, on the road, at the office, or in the classroom.

Keep up with the latest tech news, reviews and previews by subscribing to the Good Gear Guide newsletter.

Katherine Noyes

IDG News Service
Show Comments

Father’s Day Gift Guide

Most Popular Reviews

Latest News Articles

Resources

GGG Evaluation Team

Kathy Cassidy

STYLISTIC Q702

First impression on unpacking the Q702 test unit was the solid feel and clean, minimalist styling.

Anthony Grifoni

STYLISTIC Q572

For work use, Microsoft Word and Excel programs pre-installed on the device are adequate for preparing short documents.

Steph Mundell

LIFEBOOK UH574

The Fujitsu LifeBook UH574 allowed for great mobility without being obnoxiously heavy or clunky. Its twelve hours of battery life did not disappoint.

Andrew Mitsi

STYLISTIC Q702

The screen was particularly good. It is bright and visible from most angles, however heat is an issue, particularly around the Windows button on the front, and on the back where the battery housing is located.

Simon Harriott

STYLISTIC Q702

My first impression after unboxing the Q702 is that it is a nice looking unit. Styling is somewhat minimalist but very effective. The tablet part, once detached, has a nice weight, and no buttons or switches are located in awkward or intrusive positions.

Latest Jobs

Don’t have an account? Sign up here

Don't have an account? Sign up now

Forgot password?