So Many People Have Purchased Warby Parker Monocles That The Company Had To Tweak Its Recommendation Algorithm
That apparently applies to Warby Parker's monocles too.
Carl Anderson, Warby Parker's Director of Data Science who has also worked at One Kings Lane, told Data Science Weekly about his work at the eyewear e-commerce company. The complete interview is packed with interesting tidbits, but one thing that stood out to us was how Warby Parker uses its unique try-on program to make better recommendations - and how a high number of monocle purchases screwed up its basket algorithm.
Anderson told Data Science Weekly that two weeks ago, Warby Parker sent its Home Try-On recommender out for A/B testing - that's the program where users order and receive five frames free of charge so that they can try on a variety before buying.
"Unlike most e-commerce sites, our basket size is very small," Anderson says. "Customers wouldn't normally purchase a pair of glasses frequently, as they would groceries. However, our HTO program ships boxes of five frames to customers. This is a really great dataset because it is reasonably large and you can look at the covariances among the five frames plus what they subsequently purchased and build a recommender based on basket analysis. We hope that the tool will help customers better choose frames that they'll want to purchase."
The most surprising insight that Anderson found was that Warby Parker's monocles are selling at "an extremely high conversion rate" - almost everyone who ordered one to try on ended up purchasing it. The company has been selling one type of monocle, named after Col. Mustard from the movie "Clue," since 2010, and the product has become both infamous and a point of pride for the co-founder of Warby Parker.
"Conversion is so high that we had to tweak our basket analysis algorithm specifically to account for it," Anderson said.
We reached out to Warby Parker to get concrete numbers on just how many monocles have been purchased, and will update when we hear back.