Zendesk has unveiled a new a machine-learning and predictive analytics feature for customer satisfaction.
The feature, called Satisfaction Prediction, is available on Zendesk’s Enterprise plan. The feature can be leveraged to predict how likely a ticket is to receive a good or bad rating, which helps businesses take action to ensure a positive outcome. Since its beta launch five months ago, Satisfaction Prediction analyzed nearly 2 million customer interactions and has been leveraged by big-name brands, including Pinterest and Easy Taxi.
"We've been using Satisfaction Prediction to detect conversations with customers that are most at risk of a poor customer experience,” said Maggie Armato, reactive support lead at Pinterest. “Previously, we had a manual process where a dedicated team member would look through our tickets and proactively flag experiences identified as potentially negative. Now, we use the prediction score to accurately and automatically identify these types of tickets so our agents can focus on higher value areas."
Satisfaction Prediction works by leveraging machine learning to read and transform hundreds of signals including text description, number of replies and total wait time into a unique model that calculates how likely a customer is to provide a positive satisfaction rating. This calculation enables agents to prioritize workflows, drive business rules or trigger downstream integrations based on data-driven analysis.
“Customer relationships have become increasingly complicated with the rise of communications across mobile, social, and everywhere in between,” said Adrian McDermott, SVP product development at Zendesk. “We designed Satisfaction Prediction to help businesses navigate these complex relationships by bringing data into the equation. By having an early warning system that identifies high-risk interactions, companies can course-correct negative experiences before they ever even happen.”
It is important to note that Satisfaction Prediction provides users with a dashboard that gives a snapshot into the health of ticket queues, changes over time and insights into how key metrics like number of replies and reassignment volumes influence the prediction score. What’s more, the intelligent prediction models learn and improve over time with a new mechanism that learns from the feedback of customers who rate their experience and the input of agents working with the customer.
Satisfaction Prediction is generally available for all Enterprise plan customers who receive a minimum of 500 satisfaction ratings per month.