Machine Learning Times
Machine Learning Times
AI Success Depends On How You Choose This One Number
 Originally published in Forbes, March 25, 2024. To do...
Elon Musk Predicts Artificial General Intelligence In 2 Years. Here’s Why That’s Hype
 Originally published in Forbes, April 10, 2024 When OpenAI’s...
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...

10 years ago
Music Data Analyst Turns Sights to Books


In 2009, Alexander S. White, a former Universal Music Group intern, co-founded a company called Next Big Sound that analyzed vast amounts of data about musicians — from Twitter activity to Wikipedia searches to radio appearances — and showed how it affected sales.

“If we can accurately measure where people are spending their time and attention,” Mr. White said, “we can better forecast where they will spend their money.”

Now Mr. White and Next Big Sound, which counts much of the recorded music industry as clients, is bringing its analytics to book publishing.

On Sunday night, the company announced a new division, Next Big Book, and its first publishing-industry partnership, with Macmillan. For eight months, the two companies have worked together to build a tool that will, Macmillan says, “draw sales, publicity, events, social media, web traffic, and web trends data together on a daily basis.”

The idea is that the Next Big Book’s dashboard, which Macmillan plans to give to its employees and authors over the next few months, allows the publishing company to see what factors — from Facebook posts to book reviews to appearances on NPR’s “Fresh Air” — are most influential on sales.

The publishing industry has been moving toward more data collection and analysis for nearly a decade. Still, the industry’s primary data service is Nielsen’s BookScan, introduced in 2001, which collects point-of-sale data. More recently, Amazon has given sellers a dashboard that allows for in-depth time and location analysis for sales that occur through them. But Next Big Sound believes that overlaying sales data with information from social media and elsewhere vastly improves the industry’s current technology.

Fritz Foy, Macmillan’s executive vice president for digital publishing and strategic technology, said that in limited testing the Next Big Book tool had already provided insights.

“The one I couldn’t believe was the absolute overlapping correlation between traffic to an author’s Wikipedia site to book sales,” Mr. Foy said. “It is such a tight correlation that at first I thought it had to be wrong.”

The company has also found correlation between spiking interest on Goodreads, the social media site owned by Amazon and focused on books, and sales at Barnes & Noble stores.

Macmillan employees are experimenting with the data. Brittney Kleinfelter, a marketer at the company, noticed that one of her authors was selling well in the same geographic regions as a rival author who wrote similar books. As a result, she decided to move ad dollars to markets where neither author is selling well yet, but where she sees growth potential.

“We want to target our marketing campaign where the other author isn’t,” she said. “That way there will be less competition.”

By: Leslie Kaufman
Orignally published at

Leave a Reply