The Buy Box and Algorithmic Pricing in Focus

New research led by Northeastern's Christo Wilson, assistant professor in the College of Computer and Information Science, reveals that Amazon is much more likely to feature sellers in the buy box who use algorithmic pricing, even though their prices may be higher than those who don't.

Algorithmic pricing readjusts product prices in real-time using (what else) computer algorithms, reacting to variables such as competitors' changing prices and sellers' inventory levels. The research was presented at the 25th International World Wide Web Conference.

"When you go to a page on Amazon, what you're seeing is typically not the lowest price available," said Wilson. "For example, we found that 60 percent of sellers using algorithmic pricing have prices that are higher than the lowest price for a given product. Now, 70 percent of the time they only raise the price by $1, but there are many cases where the price increase is on the order of $20 to $60. So you really have to take that extra step and click through to the list of all sellers for a given product if you want to find the lowest price."

The Northeastern researchers found that Amazon actually has a relatively small percentage of algorithmic sellers - between just 2 and 10 percent - but they cover nearly one-third of the best-selling products offered by outside merchants. On average, the prices of about one-third of the products the researchers tracked changed at least once a day, prices of 170 products changed more than three times per day, and 50 changed more than eight times per day. "The prices of products offered by algo sellers were almost 10 times more volatile than products with no algo sellers," says Wilson.

Amazon uses its own proprietary algorithm to select who gets in the buy box on any given page at any given time--or, as Wilson puts it, "which seller is going to be ordained and put onto the page." But he and his colleagues gleaned some hints. A low price is part of the mix, but so is percentage of positive reviews and having Amazon Prime status. Considering feedback does benefit customers, says Wilson, but there are limits. "Suppose that you have 99 percent positive feedback and I have 95 percent positive feedback. Our research shows that you can charge a significantly higher price than I can and you will still be selected for the 'buy box.'"

Bottom line, Wilson suggests, "this is very much a winner-take-all system. If you're that one lucky seller who gets the 'buy box,' you make all the sales. So if you want to be competitive for the top-selling products, you pretty much have no choice: You have to be an algorithmic seller."

On the surface algorithmic pricing seems incredibly complicated (and it is for the most part) but there are numerous automated pricing services available including those from companies such as Sellery, Feedvisor, and RepriceIt among others that are more than capable of doing the heavy technical lifting. These companies essentially help sellers define pricing strategy (e.g. "find the lowest price offered and go above it (or below it) by X dollars or Y percentage", or "find Amazon's own price for the item and adjust up or down relative to it") and their platforms do the rest. 

If you're serious about capturing the buy box, just know that it starts with an algorithmic approach to pricing.