Proprietary next-generation receipt-scanning know-how improves accuracy with merchandise recognition, product intelligence and enhances consumer expertise

MADISON, Wis., March 7, 2023 /PRNewswire/ — Fetch, America’s No. 1 rewards app, right now introduced the launch of its next-generation laptop imaginative and prescient and product intelligence engine that enhances all points of receipt understanding, product identification, and app efficiency. The most vital product launch in Fetch historical past exterior the app itself, this suite of applied sciences is accelerating the corporate’s development and cementing its place because the world’s main consumer-engagement platform.

“Receipt understanding is a very complex problem. There is no unifying standard of what retailers print on receipts, and we have a fraction of an instant to turn a mobile image into clear, accurate, machine-readable understanding,” stated David Berk, Group President, Product and Technology for Fetch. “Today, in every dimension, Fetch scan-and-match technology is the best in the world.”

Fetch offers manufacturers the flexibility to create campaigns and run presents immediately on the Fetch platform. Technology and innovation is central to the Fetch product and repair. As the corporate has grown, Fetch has prioritized huge investments in its engineering, synthetic intelligence and machine studying groups. The fruits of a multiyear initiative involving a number of cross-functional groups, this know-how is essentially the most superior scan-and-match functionality ever constructed, accessible solely on the Fetch platform.

“We rely on document understanding machine learning models to not only read text from receipt images and label the text according to what it is describing, but to also map the line items to as specific a product as possible in our extensive product catalog,” stated Drew Crawford, Vice President Engineering.

Since launch, the next-generation laptop imaginative and prescient and product intelligence know-how has improved accuracy in textual content detection and token labeling by an order of magnitude and has enhanced app efficiency and stability for manufacturers and shoppers alike.

“Every time we increase the accuracy of our product recognition, that translates to better targeting and greater efficiency for partner brands,” says David Sommer, Chief Customer Officer for Fetch. “These improvements, combined with our unparalleled ability to activate consumers within the app and drive incremental sales, make Fetch the most powerful adtech platform on the market.”

Beyond the engineering, constructing this new know-how additionally concerned a big “boots on the ground” effort to manually practice the system on precisely acknowledge the varied product codes and abbreviations that seem on receipts. Fetch workforce members shopped at a whole lot of shops nationwide, buying gadgets, submitting receipts, and mapping out the retailer-specific codes and short-product descriptions of a whole lot of 1000’s of distinctive gadgets. Fetch donates the merchandise bought throughout this initiative to a wide range of charitable organizations throughout 17 states.

By offering a digital view of the bodily world, Fetch permits model companions to leverage this intelligence by working exactly focused presents and promotions immediately on the Fetch platform. These campaigns drive incremental gross sales by activating the extremely engaged consumer base and optimizing based mostly on quick buy suggestions from inside the closed-loop system.

About Fetch

Founded in Madison, Wis., Fetch is on a mission to assist folks have enjoyable and get monetary savings on each buy. The No. 1 rewards app available on the market, Fetch has greater than 17 million month-to-month lively customers who’ve collectively submitted greater than 5 billion receipts and earned greater than $550 million in rewards factors. A top-ranked app within the App Store and Google Play Store with greater than 4 million five-star critiques from completely happy Fetchers.

CONTACT: Allison Geyer, [email protected]

SOURCE Fetch