We teamed up with Shopify to create AI-powered product recommendations.
Jess Erdman, March 2021
Too many retailers are stuck with static product recommendation systems that aren’t delivering accurate, fashion-forward recommendations to customers. And, the product recommendation systems that do exist are either painfully expensive for small and medium businesses or unable to deliver dynamic recommendations to customers.
That’s why we decided to create the YesPlz Product Recommendation Engine, available on Shopify. Our AI learns merchants’ product catalogs within 1 day and can immediately produce fashion recommendations that customers want to click on.
We’ll go over:
When a customer clicks on a dark-colored running shoe, non-fashion forward product recommendation engines pull irrelevant results such as boots and winter shoes.
Our fashion recommendation engine is able to identify and tag key product attributes (shoe type, color, style) to suggest similar items that fit the customer profile.
In the above example, a customer is searching for a dark-colored running shoe. YesPlz’s product recommendation engine can identify the type of shoe, style, and color to suggest similar items. However, a default product recommendation engine suggests completely off-target products.
Fashion-forward recommendation engines such as YesPlz can identify a customer’s aesthetic and make relevant suggestions based on merchants’ product catalogs. By using AI that’s specifically trained in fashion, the YesPlz Product Recommendation Engine goes a step further than other systems--our AI can recognize hundreds of product attributes, categorize them, and make suggestions based on the original product viewed.
However, not all recommendation systems are made the same. If you’re using a recommendation system that isn’t well-versed in fashion, you’ll end up showing customers products that are irrelevant, outside the customer’s search intention, or simply miss the point.
Fashion and AI are at the heart of the YesPlz Product Recommendation Engine. After conducting hundreds of online shopper interviews, we came to the conclusion that current product recommendation systems simply aren’t meeting retailers’ needs. Our fashion recommendations are specifically trained in the products that customers are viewing and pull key product attributes to show customers relevant, accurate products.
Based on extensive interviews with online shoppers, we identified the characteristics that matter such as silhouette, patterns, colors, and design details. We then fed thousands of images of fashion items to our AI. We taught some fashion vocabulary, the AI became smarter, then we had our fashion analyst teach our AI how to recognize features from an image. Now our AI understands texts as well as images to accurately understand fashion styles.
Here's how it works:
But, what does that mean for retailers?
When customers are shown products that they’re interested in, they’re willing to complete purchases. A dynamic product recommendation system can also help you, the retailer, put lesser-sold items front-and-center, as recommended products. Items that are sitting in inventory, gathering dust, can result in bigger basket sizes.
Just ask Kolon Mall, a leading retailer in Korea utilizing the product recommendation system. As a result, Kolon Mall saw sales lift and a decrease in brand insulation--customers were more willing to discover new brands when shown relevant product recommendations. Because of the high relevance of the products, the YesPlz product recommendation system stood out to customers.
When customers are engaged, there are two great effects on your business: bigger basket sizes and higher rates of customer loyalty. Customers that were shown relevant product recommendations are more likely to return to your website and are also more likely to complete the purchase journey. By allowing customers to stay engaged throughout every part of the purchase journey through relevant product recommendations, you’re helping your overall business. With the YesPlz Product Recommendation Engine, retailers can target different customer personas to keep them engaged and coming back to shop.
A well-developed product recommendation system is also a way to avoid confusing text-based search queries which can deter shoppers when they don’t know the correct keywords to search for.
Keeping track of which product SKUs are sold out is frustrating--and so is manually replacing out-of-stock products. Customers easily bounce off when they see a product is sold out--so suggesting an alternative product is a best practice. With YesPlz Fashion Recommendations, retailers can show customers alternatives to out of stock products, keeping customers engaged in their shopping journey.
According to Business Insider, 49% of consumers surveyed said they've purchased a product they weren’t planning on buying after receiving a personalized recommendation. The power of personalized recommendations can have real effects on your business.
You can use the YesPlz Product Recommendation Engine to promote lesser sold products that are sitting in your inventory. When recommendations are relevant, customers are willing to purchase products.
As a best practice, product recommendation systems should be adjustable to your unique business goals. YesPlz Fashion Recommendations can be tailored to your business needs, whether you’re looking to promote a specific brand or product type--we can help you meet those goals.
Interested in learning more about the YesPlz Product Recommendation Engine for Shopify?
Fashion AI is heating up in 2022--and these are the top startups we've named that are shaking up the industry, creating new ways to keep customers engaged.
NLP in eCommerce is used to build text-based fashion search for shoppers. But, as any frustrated shopper knows, NLP can only capture part of the language of eCommerce. We explore the problems and solutions to text-based search, and how visual and text-based search can complement each other.
Product recommendations are at the core of the eCommerce search experience. A good product recommendation can make the difference between conversion and shopper satisfaction. In our latest series, we review two retailers' product recommendation systems, and determine which is stronger based on YesPlz criteria.
Your request has been submitted successfully.
Our representative will reach out to you within 24 hours.
Contact us at email@example.com for any further questions.