A friend alerted me to this paper by Vikas Ganjigunte Ashok, Song Feng and Yejin Cho (Stony Brook University, Department of Computer Science):

“Predicting the success of literary works is a curious question among publishers and aspiring writers alike. We examine the quantitative connection, if any, between writing style and successful literature. Based on novels over several different genres, we probe the predictive power of statistical stylometry in discriminating successful literary works, and identify characteristic stylistic elements that are more prominent in successful writings. Our study reports for the first time that statistical stylometry can be surprisingly effective in discriminating highly successful literature from less successful counterpart, achieving accuracy up to 84%.”

Reaad the paper here.

Especially when it comes to commercial fiction, and what else is left besides commercial fiction, a few ghettos or well gated communities, we can start exchanging acquiring editors for software, highly sophisticated algorithms.