Several years ago, I waited 45 minutes in the queue just to buy a simple beverage and I thought whether we really need cashiers in retailers, or not. I knew the answer was no. In my opinion, it was possible to walk in, grab whatever you like and leave with a self-checkout system. However, because of the lack of technical knowledge, I could not come up with a brilliant idea. The only idea came to my mind was RFID (Radio-frequency identification) tags. The idea was simple; tag every product with RFID tags (like we see on books or DVDs) that will enable customers to scan each product with their smartphone –Near Field Communication (NFC) technology is standard for most of the smartphones today- and add the products to their cart and pay online.
Although the idea seems good, it was not functional. Changing the barcode system is not that easy. Additionally, even if it reduces the labor cost, tagging each product with RFIDs decreases the gross profit margin. Still, the pitch of the idea provided me an A from an entrepreneurship course at school. Today, self-checkout systems are attracting attention from tech giants like Amazon and Walmart. According to surveys, 60% of people are irritated with long checkout lines.
This article explains all different approaches to self-checkout, provides examples from companies and highlights challenges of self-checkout systems.
Different approaches to self-checkout
There are different traditional checkouts with different pros and cons:
Some convenience stores have already been using self-checkout machines in their stores for a few years. They have some advantages:
- Shorter lines and faster checkout
- Improved privacy
- Greater accuracy
- Reduced labor cost
- Better in-store optimization thanks to availability of new space with reduction of queues
- Improved Customer experience
However, they are not the ultimate solution for fully automated checkout since the customer needs to still checkout items one by one. I was in the queue for one of these machines. Moreover, implementation costs are high. A typical four-lane setup costs $125,000 to install. For more information, you can read The Conversation’s article about self-service checkouts.
Self-checkout units with RFID
DXC Technology along with Harting Systems and Murata launched a new RFID-based self-checkout counter in 2020 (Yes, it appeared that I was not alone). Retailers can label all their products with RFID tags. When costumers place their shopping bag on the counter, all the products get scanned at once without any effort and counter displays a full list of the products and total price.
This technology reduces the time spent on the entire checkout experience to 30 seconds.
For this technology to work, all items need to be tagged with RFID tags and these potentially expensive checkout machines need to be installed in stores.
A company called Automated Stores produces customized vending machines to provide automated checkout experience.
Vending machines automates the checkout experience and is potentially more secure than other approaches. However, vending machines put a glass between products and customers and do not allow them to touch products before buying. In addition, these machines are also expensive hardware.
Walmart Scan & Go App
Walmart’s solution for autonomous checkout system is really simple (It resembles my idea actually; I thought RFID tags are better in terms of security). Walmart introduced the Scan & Go program in select stores between 2012 and 2014. The app basically allows customers to scan the products with their smartphones and pay by scanning a barcode for their total purchase and pay for their goods. Compared to other systems, this is the easiest to deploy system however creates additional work for customers. Due to customers’ negative feedback about the confusing process of bagging, weighing and then scanning items, the company ended the program in 2018 .
In 2018, Walmart launched a new service called “Check Out With Me,” where employees can interact with customers, scan their order and payment card from a handheld device inside the store. The new service is now available in more than 350 lawn and garden centers. Even though it is not a self-checkout solution, it provides some benefits such as reducing queues.
As of June 2020, Walmart is testing new self-checkout kiosks at a store in Fayetteville, Ark. In this checkout experience, Walmart combined self-checkout system with human-guidance where a host is always available to make the checkout frictionless.
AI and image recognition will boost self-checkout
In general, the main reason for long waiting times in long checkout lines is Point of Sale (POS) systems and POS devices. Traditional scanning and payment processes cause increase in waiting times whether you are in a convenience store or supermarket or H&M. There are software solutions for payments. One of the key features of automated checkout systems is online payment with a pre-registered credit card.
Here, 2 people randomly picking items from shelves to demonstrate Standart Cognition’s technology.
The company uses computer vision technology to track people and the products in real-time in the store. Deep learning and image recognition technics enable Standard Cognition to recognize items. Brandon Ogle, co-founder and an engineer said that the system is currently correct 98 percent of the time. You can find out more about the technology in the article written by Rachel Metz on MIT Technology review.
Online retailer Amazon opened its beta version of the cashierless store on 5th of December in 2016 in Seattle. The 1800-square-foot retail store was only for employees. Then the store become open to public on January 22, 2018. As of 2021, there are 27 Amazon Go stores that are located in 4 different states: Chicago, New York, San Francisco, Seattle.
Amazon also uses computer vision and deep learning algorithms like Standard Cognition. Amazon calls this technology “Just Walk Out” and uses approaches used in in autonomous driving vehicles. Amazon uses various cameras and sensors to see what customers are putting into their shopping bags. Customers scan a QR code when they enter the store through an app, which is connected to their Amazon.com account. After shopping, customers can simply leave the store. Amazon automatically charges the customers’ Amazon account and receipt is sent to the app.
It took quite some effort to improve the system. During the pilot, Amazon employees have been trying to fool the system with though challenges like wearing Pikachu costumes while shopping. Though the system passed the costume test, it has a hard time to detect customers who shop in groups, such as families.
Funnily, the Go stores which are meant to reduce queues were causing queues during their initial launch as people lined up to see how they work:
” I’m in Seattle and there is currently a line to shop at the grocery store whose entire premise is that you won’t have to wait in line.” Ryan Petersen (@typesfast)
Wheelys had a concept like Uber for retail. they provided different mobile sales vehicles and experimented with mobile stores that enabled self-checkout. However, with the COVID-19, they couldn’t raise a series A and ceased operations.
They had developed a store called Moby where customers can enter through sliding glass door with an app including their pre-registered credit card information. In the store, there is no employee, no cashier, no queue, no waiting. Customers scan and bag the products (including fruits, potato chips, coffee, magazines, and even sneakers) with the app and then leave. The app automatically charged the customers.
The Swedish company was testing the 24-hour mobile grocery store in Shangai. The store was also planned to be a self-driving vehicle. However, the self-driving technology was never implemented yet. The company was claiming that Amazon Go copied their idea before they stopped operations.
SmartCart solutions such as Imagr
Long before Amazon and Standard Cognition, Imagr published a video showing its SmartCart powered by image recognition technology. Once you link your phone to the cart with an app, scanning is not necessary, computer vision system recognizes the products in the cart. Then you just pay online via the app and leave the store.
Imagr was founded in 2015 and they now have some pilot deployments in countries such as Japan.
Barcode scanning solutions such as Snabble
Snabble is an app that enables customers to scan their purchases in retail stores, pay online and then walk out. The app is in use in markets called Knauber in Germany and Frankfurt IKEA. Though Snabble app is good overall, there are some problems, while reading barcodes, such as
- Low print quality of a barcode is too low
- Low quality of your mobile phone camera
- Certain barcodes are not priced in the system.
The system also provides limited security for retailers as end users are in charge of the whole process.
Cons of self-checkout systems
Even though it sounds like amazing and provides peerless customer experience while reducing labor cost, it has some disadvantages.
- All purchases and transactions are made online with pre-registered credit card information. Some users will be reluctant to get their credit cards stored
- Inventory Loss No matter how advanced the technology is, there will be people trying to steal because employees are unable to monitor customer transactions as closely on self-checkouts. While some technologies try to minimize theft, some technologies such as barcode scanning solutions rely on users’ compliance.
- Lack of Personal Interaction
- Although the key benefit is eliminating the customer engagement to decrease waiting times, customers may prefer to have a one-on-one interaction with cashiers.
- Implementation difficulties
- Sometimes bar codes and coupons don’t scan properly, some products such as alcoholic beverages require age verification, or customers need assistance
Interested in trying this out at your business and looking for an AI vendor? Let us know
How can we do better?
Your feedback is valuable. We will do our best to improve our work based on it.