NytDemo is a cross-functional team comprising members of the publisher’s data, product and design, technology and advertising groups. The aim of the team is to develop data-led commercial products based on the publisher’s audience insights.

The first tool to be launched from the team, Project Feels, used machine learning to understand and predict how emotions connect with reader engagement. NytDemo has used the machine learning behind the project to launch a perspective targeting product which allows advertisers to target media based on content that is predicted to evoke specific reader sentiments.

The publisher is also planning to launch an artificial intelligence data insights tool, Readerscope, that uses anonymised data to summarise what audiences are reading and visualise which topics readers are interested in. The tool will eventually be able to create custom segments, based on advertisers’ first-party data, for a specific audience, the company has said.

Allison Murphy, vice-president of advertising innovation for the New York Times, said: “We see insights as the next frontier for the Times advertising business. We have to make a product that’s worth paying for, which means we have to know our audience with extraordinary depth and turn those insights into engaging products.”

She added: “We’ve created nytDemo to transform our audience understanding into ad products and tools, inviting brands to tap into our knowledge.”

Chris Wiggins, chief data scientist at the New York Times, said Project Feels and Readerscope “grew out of our internal innovations using machine learning to understand our readers better.”