GlassesUSA sees the clear benefits of dynamic performance
glassesUSA.com is one of the largest online eyewear stores, selling top brands like Ray-Ban and Oakley and their own products in over 190 countries. The New York-based company uses advanced tools to help customers select the right frames and the best fits at competitive prices.
“We promise satisfaction; we have very high level return policies, money back guarantee, insurance and much more, said Ben Blanki, director of product labs at GlassesUSA, who adds that the company has experienced strong growth over the past few years. years.
But GlassesUSA always wanted to better understand their customers so that they could make better recommendations. “We put our customers at the center of everything we do. Instead of giving generic recommendations, we wanted to build on what someone had already seen, loaded into their shopping cart, etc. We also wanted to be able to do A / B testing, which in my opinion is essential for the growth of e-commerce, ”said Blanki. said.
GlassesUSA started looking for a supplier almost three years ago and finally chose Dynamic Yield.
Although the initial relationship with Dynamic Yield started around 30 months ago, GlassesUSA has become a beta tester for Dynamic Yield’s deep learning recommendations algorithm to deliver enhanced recommendations to customers towards the end. from 2019.
“When we first tried it the results were amazing. We saw a huge increase in conversion, so we implemented it fully, ”recalls Blanki.
Implementing the algorithm was the hardest part, according to Blanki. “It takes time and resources to see results. “
The initial implementation did not go as well as hoped, Blanki admits, attributing the poor initial results to the lack of dedicated time and resources of his own business. But once GlassesUSA began to see the great value that was possible, they made the commitment. When the back-end was fully developed, the speed of the recommendations provided by the algorithm improved significantly, meaning that its use did not slow down the ecommerce process.
“The background is the most expensive part, but it was worth it,” says Blanki. “It took a little less than three weeks to fully implement the solution, with the APIs. “
Today Blanki sees Dynamic Yield more as a partner than just a commercial supplier.
GlassesUSA achieved rapid results once the Dynamic Yield deep learning algorithm was fully implemented. These included an 87% growth in revenue, a 68% increase in purchases, and a double-digit increase in the add to cart rate (the percentage of customers who make an initial selection, then add additional items to their cart before checking out).
Dynamic Yield’s algorithm also provides GlassesUSA.com with better A / B tests, explains Blanki. “Now I test different strategies every two or three weeks. “
These strategies include adjustments to the home page and subsequent category pages, according to Blanki. “Our culture of A / B testing has really grown.”
Going forward, GlassesUSA plans to continue to rely on Dynamic Yield as it further seeks to personalize and optimize its site. The changes being considered include the placement of recommendations on the site as well as mixing it up a bit for all customers, for new customers, for repeat customers, etc.
“We will be testing many types of placements for different views and different strategies,” Blanki said. “This is the first step towards a more personalized approach for our customers. It will be more of an Amazon-type approach. We’re going to look at changes to small features that can increase conversion rates. ”
Through the use of Dynamic Yield’s deep learning recommendations algorithm, GlassesUSA.com achieved the following results:
- 87% growth in turnover;
- a 68 percent increase in purchases; and
- a double-digit increase in the add-to-cart rate.