AI
Instacart Acquires Arpalus to Advance Real-Time Shelf Intelligence Across Grocery Retail
Instacart (NASDAQ: CART), the leading grocery technology company in North America, today announced its acquisition of Arpalus, a computer vision company that has developed shelf intelligence technology purpose-built for grocery retail. The accuracy of online orders is only as good as the underlying inventory data – undetected out-of-stocks and catalog gaps are among the most persistent sources of customer dissatisfaction in online grocery, driving substitutions, cancellations, and eroded trust.
About this update from Maplebear Inc.
Acquisition strengthens Instacart's AI capabilities and purpose-built partner technology to improve inventory accuracy for ecommerce fulfillment and in-store operations across its network SAN FRANCISCO, July 16, 2026 /PRNewswire/ -- Instacart (NASDAQ: CART), the leading grocery technology company in North America, today announced its acquisition of Arpalus, a computer vision company that has developed shelf intelligence technology purpose-built for grocery retail. The accuracy of online orders is only as good as the underlying inventory data – undetected out-of-stocks and catalog gaps are among the most persistent sources of customer dissatisfaction in online grocery, driving substitutions, cancellations, and eroded trust. The acquisition enhances Instacart's ability to serve consumers, shoppers, retailers, and brands with a more complete picture of on-shelf inventory and product availability — a foundational input that increases fulfillment accuracy , creates more relevant AI-powered consumer shopping experiences , and delivers additional in-store capabilities . Arpalus' technology turns a quick video scan of a store shelf into an accurate, real-time picture of what is actually there. Using computer vision models built specifically for the complexity of real grocery store environments, including low or unreliable Wi-Fi, inconsistent lighting, and thousands of visually similar products packed tightly together, Arpalus can identify individual items on shelves with more than 95% accuracy, on average. The technology runs on any smartphone or camera-equipped device, which means Instacart's network of 600,000 shoppers can generate real-time shelf intelligence at scale using the app they already use on every order. Arpalus models can also guide shoppers in the moment, prompting them to adjust camera angle or distance to ensure every item on the shelf is captured accurately and efficiently. Instacart has spent more than a decade building the most comprehensive grocery-specific intelligence in the industry — built on more than 1.6 billion lifetime orders, real-time inventory views from nearly 100,000 stores across North America, and proprietary ML models purpose-built for grocery. At the center of that system is a community of 600,000 Instacart shoppers who visit large-format stores more than 15 times a day on average, generating over 10 million unique daily data points. Every order placed, item picked, and substitution made feeds directly back into Instacart's models, creating a continuously improving picture of real-world store conditions that takes years and significant scale to build. This results in an industry-leading found rate — and with Arpalus' shelf intelligence now part of this system, Instacart can drive that rate even higher, moving closer to a future where every item a customer orders is seamlessly delivered to their door.