How Retailers Use AI To Predict When You’ll Buy

Can AI predict when you’re going to buy a product?

Or if you’re just window shopping?

“It absolutely can,” Adobe director Steve Hammond told me in a recent TechFirst podcast. “It needs certain points of data input to help with that, but it is a big part of how we have interactions across journeys today.”

Those interactions are the “customer journey.”

Marketers call the actions you take before purchasing a product the customer journey. It could include seeing an ad, or hearing about a product from a friend. It probably involves some searching on Google. You might buy it right away, or you might get distracted, never to actually purchase the item you were once interested in. One marketer I talked to told me he had mapped over 800 different customer journeys, but in reality, there’s probably as many as there are people interested in any given product.

That’s where AI can help brands and retailers.

“There are any number — an infinite number — of possible journeys that someone could take,” Hammon says. “So it’s important that AI can help with that because the real challenge is that when you try to get a team of people to create a path, the ideal path for an individual, it’s never right because you can’t create that infinite number of paths.”

No human can possibly imagine the scope of all those different touchpoints. Plus, a brand actually only sees a small percentage of them: perhaps an ad click and a website visit. That’s where Adobe cooked up a skunkworks project they dubbed “Bon Voyage” to apply personalization to infinite customer journeys via the company’s AI engine, Sensei.

Bon Voyage uses historical data to understand customer journeys, because even when we take infinite paths, the 80-20 rule does apply. Then it also looks at the specifics of what each individual is doing now, and attempts to optimize the future flow.