Predictions are artificial intelligence’s (AI) forte, you might say. Some of the most accurate machine learning models draw on hundreds of thousands (or even millions) of data points to surface patterns that would otherwise go undetected. Adobe is using AI to predict when to send marketing emails. Gogo is tapping it to predict equipment failures. And Nuance claims it can be used to deliver tailored, proactive service to customers.

Nuance this week announced Nuance Prediction Service (NPS), a new tool within its Customer Engagement Platform that enables brands to forecast client behavior and respond in an automated, contextualized fashion. It aggregates data from transactions “across all channels” — including the web, text messages, apps, internet of things devices, and more — to fuel its prediction models, over time refining them with “constant analysis.”

“Large organizations today are fielding billions of customer interactions each year, and being able to anticipate and resolve customer needs in advance offers not only enormous potential for savings and operating efficiencies, but perhaps more critical, advances the customer experience,” Robert Weideman, executive vice president and general manager of Nuance’s Enterprise Division, said. “Prediction Service fuels the kind of highly personalized, omnichannel strategy that so many organizations are trying to achieve to engage their customers intelligently, while providing self-service that makes tremendous impact on efficiencies.”

Nuance claims NPS can improve containment rates, routing accuracy, conversion rates, and…