Can Artificial Intelligence Finally End Email Overload?

Adobe is trying, with its new machine learning tool

If you have ever bought something from an online store, chances are the store’s used your email address with wanton disregard, bombarding you with email after email about its products and sales until you reach for the sweet oblivion of unsubscription.

Stores and brands do this to keep customers engaged—but they don’t know how many emails are too many. Adobe previewed a tool today with the promise to help alleviate what they call “customer fatigue.” By using machine learning algorithms to crunch the numbers of how often emails are opened and clicked on, marketers can see whether customers are tired of getting their emails. The algorithms will allow Adobe to actually calculate how fatigued every customer might be, and only send a certain number of emails based on that score.

It takes Adobe’s system, called the Customer Fatigue Dashboard, about a month to become tailored to a certain brand, but then it can recommend specifically how many emails the average customer will be open to receiving before clicking Unsubscribe. Brands will now be able to figure out the exact threshold between annoyance and unsubscription.

The dashboard of Adobe Marketing Cloud
Here’s how marketers will be able to tell if you’re getting too many emails. Adobe

Users of the Dashboard will see customers divided into three categories: active, at risk, and fatigued. Active customers love your emails, at-risk ones click on them less, and the fatigued have given up on you entirely. According to Mathieu Hannouz, who works with clients on Adobe’s Marketing Cloud, the trick is to have most users active, though it’s okay to have some at risk. And the algorithm can predict this fatigue into the future, by looking at numbers of the past.

“I can just play around with these numbers, and I can see the potential effect of the erosion of my database,” Hannouz said.

However, these fatigues aren’t static. People might want more email for gift ideas in the winter than in the summer. Hannouz says the second step of the platform is to train on data from various industries so they can take into account larger events that influence buying, like seasons. The