Zendesk’s Satisfaction Prediction Brings Machine Learning to the Customer Experience

PRESS RELEASE: Zendesk announced Satisfaction Prediction – the first machine learning and predictive analytics feature for customer satisfaction – Is available to Zendesk customers on the Enterprise plan. Satisfaction Prediction leverages machine learning to predict how likely a ticket is to receive a good or bad rating, helping organisations take action to ensure positive outcomes. Since launching in beta five months ago, Satisfaction Prediction has analysed over 1.82 million customer interactions and has been successfully deployed by businesses globally including Pinterest, Digitec, 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.”

“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.”

Satisfaction Prediction uses machine learning to read and transform hundreds of signals including text description, number of replies and total wait time into a unique model that dynamically calculates how likely a customer is to provide a positive satisfaction rating. This rating allows agents to prioritise workflows, drive business rules, or trigger downstream integrations based on data-driven analysis.

New features released for Satisfaction Prediction include:

● Simple dashboard analytics: provides 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.
● Real-time feedback: intelligent prediction models learn and improve over time with a new mechanism which learns from the feedback of customers who rate their experience and the input of agents working with the customer.

“The volume of customer data is increasing rapidly with the use of digital channels. As a result, the demand for real-time solutions to facilitate faster decision-making at critical points in the customer journey is increasing,” said Aphrodite Brinsmead, Principal Analyst at Ovum Research*. “With Satisfaction Prediction, Zendesk customers do not need to employ a data scientist or worry about gathering relevant data; the feature simply predicts and identifies more sensitive queries, prevents customers from churning, and improves satisfaction rates.”