Frank + Oak Uses AI To Recommend Purchases

Frank + Oak is utilizing a  new e-commerce purchase prediction platform that uses artificial intelligence, machine learning and image analysis technology to recreate the offline shopping experience online. Propulse provides retailers with sales tools to present customers with new items, not previously purchased ones.
 
"Frank + Oak has always been about offering an incomparable level of experience to its customer base through personalization and innovation,” says Ethan Song, CEO and co-founder at Frank + Oak. "With Propulse, we're able to complement our democratized current personal stylist offer by showcasing new items to our customers that pair well with existing ones they selected - That’s what keeps them coming back for more and deepens our relationship with our community."
 

Features include:

Adapting to Consumers Shopping Behavior: Propulse recommends products using its proprietary deep learning, image recognition engine called the “Purchase Path Neural Network”. This new algorithm adapts to consumer preferences over time–helping fuel personalization and product discovery for shoppers.

Machine Learning Determines What You’ll Purchase Next: Current machine learning can’t account for nuances in personal taste. Propulse analyzes thousands of variables simultaneously for each product image to determine what the shopper is looking for at the moment, as well as offering products they’ll want to purchase after.

Enhances Buying Effectiveness with Shadow Inventory Analysis: If a customer is recommended an item while shopping online but the product is not available based on inventory, Propulse logs this interaction between customer and product in its “Shadow Inventory” and feeds that intelligence to retailers helping them understand what they should buy and to reduce retail markdowns.