A cashierless store (also called a till-less store, checkout-free store or just walk out store) is a store which allows customers to shop their products and leave without having to wait in line and pay at a checkout. Cashierless stores can currently be found in the United States, Asia, Europe, the Middle East, and Africa.

The process of shopping in a cashierless store can be broken down into four phases:

In cashierless stores, most systems mark each customer with defining features and use cameras and pressure sensors together to keep track of where each customer goes and takes from the shelves. Sensor fusion gathers information from different sensors and compiles it to create an accurate representation of what is happening and the relative positions of objects in an area at a specific time. Sensor fusion is often more accurate than single sensors since the separate measurements can be used to double-check and narrow the margin of error.

Deep learning for computer vision is used in cashierless stores to track customers and products. Computer vision is the computer’s ability to interpret real-life images and video feeds. Computer vision uses deep learning to make interpretations of the real world. Deep learning allows computers to learn from large amounts of data similarly to how the human brain would. Deep learning for computer vision tracks customers and products using object detection, multitarget tracking, and pose estimation. Object detection is the process of identifying objects within an image. Object detection is useful in identifying instances when a customer picks up and puts down an object, or for identifying the products on each of the shelves. Multitarget tracking approximately locates a moving person within consecutive frames of images. Multitarget tracking allows stores to keep track of each customer and their actions, like what products they picked up and put back and when they entered and exited the store. Pose estimation is the process of using an image to track a person using the positions of their body parts, like their head, hands, and wrists. Similar to multitarget tracking, pose estimation allows stores to keep track of customers providing information for the computer to determine which customer interacted with the store, like when a product is grabbed.

Inadequacies in Amazon's automatic tracking required over a thousand employees in India to label videos to allocate purchases to shoppers. As a result, the company in 2024 announced it would remove its "Just Walk Out" technology from its Amazon Fresh stores.

In 2016, Amazon announced the opening of its first cashierless store, Amazon Go, which opened in 2018. To shop, customers were required to have the Amazon app (formerly a specific Amazon Go app) so that they could be billed for their purchases afterward through their accounts. Amazon introduced its cashierless technology in two Whole Foods stores located in Washington, D.C., and Sherman Oaks, California, in 2022.

In January 2021, the Hudson Group, a travel retailer, announced that it would be implementing Amazon's Just Walk Out technology in select airport convenience stores, branded as Hudson Nonstop.

In June 2021, San Diego’s first fully automated and cashierless store, Valet Market, was opened to the public. Valet market is powered by the technology company Accel Robotics which utilizes an advanced machine learning AI platform that optimizes efficiency in local markets. There are three ways of shopping at Valet Store: Hub Store, Satellite Store, and Last Step Delivery.