Parham Aarabi, chief executive officer and founder of Pre, took the stage at the Apparel & Retail CEO Summit to share the impetus behind launching his company, which helps retailers optimize their websites based on simulating consumer behavior.
Aarabi began his presentation, titled “Optimizing Websites for Maximum Impact: Predicting and Adapting to User Behavior,” by noting he founded ModiFace (now owned by L’Oréal) and has seen try-on technology evolve over time.
“There are new technologies and buzzwords in the beauty and fashion industries, but the key question is: Do they work?” Aarabi said. “And perhaps a more relevant question is: Do they work for your unique brand and your unique audience?”
Related Articles
Aarabi said the impetus behind founding his new company, Pre, was based on observations of try-on technology that often performed “very differently on different sites, and often different sites would have that have the same demographic and similar audiences but would have very different conversions.”
You May Also Like
The AI-powered Pre predicts conversion performance “based only on mockups and screenshots,” Aarabi said, adding that there’s no need to implement anything. It’s done through the platform and mimics consumer behavior. There’s no need for live A/B testing or installing APIs.
“First, we start with screenshots of a site — you actually take every page of the site,” he explained. “Then we decompose the site of every element and every image and every button, and so on, for each of these. The AI then analyzes how likely users will interact with an item — including placement and size, but also user intent.”
The technology can run simulations using virtual AI shoppers to reveal behavior and preferences for various products and searches. Aarabi then demonstrated the technology by animating a screenshot of the product display page. The AI’s cursor moved about as a real online shopper would navigate a page.
Aarabi said the “fun starts when you make site changes around the user experience and redo the AI simulations. And within seconds, it tells you how the changes impacted conversions. And by using mockups, you don’t have to implement any code or anything. The AI tells how changes helped or hurt conversions.”
“All of this is contingent on the AI simulations being accurate — mimicking the actual human experience on the site,” Aarabi said. “So, accuracy is quite key.”
He said when the company’s technology launched about a year ago, his team and retail partners were at the early stages of truly mimicking human behavior. “So, accuracy, initially, was low,” Aarabi said. “But with every partnership, we kept asking, ‘What can we do better and what mistakes do we make that we don’t make again?’ So, we learn from those mistakes, and we truly train the AI. And today, we find that we can predict with 90 percent accuracy.”