Jodi Archer, a former employee at Penguin UK, and Matthew L. Jockers, a co-founder of the Stanford Literary Lab, teamed up to answer what is undoubtedly the most prevalent question facing publishers today;  “How could you know which books would be blockbusters and which would flop, and why?” Their solution to solving the “bestseller” problem involved feeding 5,000 fiction titles published over the last 30 years into computers and using the algorithms to isolate features most common in best sellers.

Their findings, which are detailed in The Bestseller Code, suggest that these algorithms can predict, with 80% accuracy, which novels will become best sellers. Among the 2,799 features listed as being strongly associated with bestsellers are: young, strong heroines who are misfits, frequent use of the verb “need”,and a sense of human closeness.

There are a handful of startup companies in the publishing industry that are creating their own algorithms or other data-driven approaches in order to replace “gut instinct and wishful thinking” with cold hard data. Callisto Media, based in Berkeley California, is using “big data analysis to find out where there’s an audience clamoring for a nonfiction book that doesn’t exist yet,” and then hiring someone to write it.

While Jockers suggests that “computers could peer into books in a way that people never could,” the effect of these algorithm and data-driven approaches on the reader is yet to be determined. Katherine Flynn, a partner at Boston-based literary agency Kneerim & Williams, suggests the risk of data-driven publishing is its potential to prevent readers from being “exposed to things they [you] wouldn’t have necessarily thought they [you] liked….It’s sad to think data could narrow our tastes and possibilities.”

However, Benjamin Wayne, Callisto’s founder and CEO, argues that “In a world of almost infinite consumer data the idea that you cannot say with specificity what a consumer will want to buy seems frankly ludicrous.” Considering Callisto Media was named one of the fastest-growing independent publishers for 2015 and 2016 by Publishers Weekly, it’s likely that more and more publishers will begin implementing algorithm and data-driven approaches to help them pick titles that best suit their audience base.

Although this still remains a topic of debate among professionals in the publishing industry, Andrew Weber, the global chief operating officer for Macmillan Publishers, raises a point that even those in opposition to a data-driven publishing landscape can’t deny, “Whether it’s in acquisition, whether it’s in pricing, whether it’s in marketing, whether it’s in distribution, there just seem to be many, many, many opportunities to improve the quality of our decision making-and therefore hopefully our results-by bringing data into the equation….we are still in the early days of that journey, but that’s the direction we’re headed.”

Read the full article here:

Algorithms Could Save Book Publishing—But Ruin Novels