CASE STUDY: Auchan Innovates with Automated On-Shelf Availability

A supermarket shelf with bounding boxes around the products
The pace of change in retail is daunting but automation offers a relief. (Image by author)

The Modern Supermarket: Adapt to Survive

“It is not the strongest of the species that survives, nor the most intelligent that survives. It is the one that is most adaptable to change.”
Charles Darwin

The retail landscape is an ever-changing one. Even the biggest players in retail face a daily battle to maintain their position in the market. But, today’s largest supermarkets may not hold their position for long simply because of their gargantuan size.

In fact, most of the largest retailers find it difficult to adapt quickly enough to the rapidly evolving demands of the modern retail customer, one that expects convenience and availability at all times.

Take the emergence of the multitude of on-demand grocery startups and their innovative use of dark stores as a clear sign that the retail industry is rife for disruption. For the incumbents in the grocery space, adaptability and rapid innovation are simply crucial for survival.

empty supermarket shelves
Empty shelves have become more common for customers as supermarkets struggle to keep up with demand. (Photo by Wesley Tingey on Unsplash)

An Automated Response to Change

Making the necessary operational changes required to meet ever-shifting consumer trends is a daunting task. Retail is an industry in constant flux and the pace of innovation can make it difficult for even the largest and most capable of retailers to keep up with.

For successful supermarket groups, maintaining a share of the retail market means adapting and innovating in three key areas: people, process, and technology.

One retailer in particular, Auchan, is leading the charge and innovating on all fronts.

Despite the rapidly changing demands of the grocery sector, their savvy use of the latest and most capable automation technology allows them to continue to do what their brand is known best for, keeping their customers happy.

Auchan: Leading the Way in Grocery Store Innovation

In the grocery business for over 55 years, French multinational retail group, Auchan, is no newcomer when it comes to meeting constantly changing consumer expectations.

Embracing the digital transition is at the heart of their strategy to succeed under increasing customer demand for reliable in-store availability and instant convenience.

Empowering their people with the right processes and tools to get their job done most effectively was a priority as they set out to optimise On-Shelf Availability (OSA) in their stores.

Auchan takes a very proactive approach when it comes to choosing the right system for improving in-store experience with digitisation. They are diligent and strategic when it comes to choosing a solution that will withstand the test of time and easily scale across their many locations.

To maintain optimum in-store throughput and to help preserve their long-standing reputation for reliability, they have turned to the productivity-increasing promises of automation.

Auchan is trialling Neurolabs’s “ReShelf” technology to monitor its shelves in real time for On-Shelf Availability and Planogram Compliance. (Video by Author)

Enter Synthetic Computer Vision

Cashierless checkouts get a ton of mainstream media attention, and for good reason. The technology radically improves throughput for retailers, removing unnecessary bottlenecks with the best that retail automation currently has to offer.

It is undoubtedly worthy of the proverbial pedestal but there is another piece of retail automation technology, one that is quickly disrupting the status quo for in-store availability, that is equally worthy — Synthetic Computer Vision (SCV).

SCV is the culmination of 60 years of advanced research into artificial intelligence and 3D geometrical mapping. The result is software that teaches computers how to interpret what they see in the real world for real-time shelf analysis.

Automation in Sight

In layman’s terms, it provides sight to computers and allows them to automate visual-based tasks.

For retailers, it automates the operational decisions and processes that are traditionally carried out manually by supermarket staff.

Neurolabs utilises SCV in their product, ReShelf, which automates On-Shelf Availability and Planogram Compliance, resulting in happier customers and increased revenue.

Auchan has successfully trialled ReShelf to manage On-Shelf Availability and are already reaping the rewards of the future of retail technology.

real-time shelf monitoring in action
Supermarket products as well as Out-of-Stocks are detected in real time. (GIF by author)

On-Shelf Innovation at Auchan

Auchan is leading the charge in retail innovation by trialling Neurolabs’ Synthetic Computer Vision technology. The goal being to put an end to the Out-Of-Stock problem for good.

Increased pressure on their stores to deliver outstanding customer experience meant they needed to do more than just identify gaps on shelves and fill them.

To avoid simply reacting to stockouts and to ensure that a truly proactive solution was implemented, Auchan needed to address the root cause of any Out-Of-Stocks that occurred in their stores.

This meant identifying and addressing fundamental process issues between their front-stores and the rest of their supply chain, requiring the integration of their stock, order, planogram, and product catalogue databases. Neurolabs’ ReShelf software helped them do just that.

Executing A Successful Trial

As part of a trial deployment in one of Auchan’s stores in Romania, Neurolabs teamed up with, Robotic Process Automation giant, UiPath to create a solution that was tailored to the requirements of their specific supermarket environment.

At its most basic level, the implemented On-Shelf Availability solution involves hardware, in the form of in-store cameras, that are pointed towards the supermarket shelves.

These cameras collect images which act as input data for Neurolabs’ ReShelf. Our Synthetic Computer Vision software then runs detections on these images to determine if there are any products that are low or out of stock.

This detection data can then be accessed from Neurolabs’ ReShelf via API in the retailer’s automation software of choice.

a preview of the Neurolabs’ platform in action with 3D supermarket products
The Neurolabs’ platform helps retailers easily detect any consumer packaged good using 3D synthetic data. (Image by Author)

Automation Without Limits

Empowered with this real-time product detection data, the supermarket can automate processes such as instantly notifying store staff of a product that is low or out of stock so that they can replenish the shelves as soon as possible.

It also provides the store with access to the most recent and useful analytics on their inventory to make the most effective decisions. This helps store managers focus on proactive decision-making versus simply reacting to in-store inventory fluctuations on the fly.

This holistic approach to in-store availability and inventory management is the new necessity for supermarkets to operate at maximum efficiency. Automation-enabled smart workflows with actionable insights like this are the future for supermarkets that hope to thrive in the retail industry.

an analytics dashboard containing information about on-shelf availability
An example of a typical On-Shelf Availability report using Neurolabs’ ReShelf. (Image by Author)

Before ReShelf

Before the trial, Auchan had store employees manually check each aisle and record the stock availability of an SKU (Stock-Keeping Unit) at pre-agreed intervals. Besides the fact that it is such an onerous process, Auchan had little to none shelf visibility in between these inventory checking sessions.

These stock level records were then used by the Auchan team to manually compare across multiple different internal systems with the goal of understanding why there is a gap on a shelf to begin with. This is workflow standard practice for the majority of supermarkets.

After ReShelf

The first change that Neurolabs helped introduce for Auchan was a way to have full visibility across each shelf at any time. Secondly we created an automated workflow that identified the root cause of each Out-Of-Stock.

Based on the gathered insights, certain actions are now automated and the right information is automatically shared with the right people at the right time, empowering Auchan’s in-store staff to address the issues the moment they occur.

quote from Auchan about the impact Neurolabs has had on their
Synthetic Computer Vision is making a big difference in store for Auchan. (Image by Author)

The result for Auchan is real-time visibility of their shelves and an end to Out-Of-Stocks. More importantly this means a more efficient workforce, increased customer satisfaction, and a significant boost in sales.

quote from Auchan about the Neurolabs’ On-Shelf Availability solution
Increased consumer demand calls for increased innovation. Auchan is leading the charge. (Image by Author)

Digitised Consumer Packaged Goods

ReShelf uses SCV technology to carry out real-time shelf monitoring and automated root cause analysis on any of the missing Stock-Keeping Units (SKUs) that it detects.

ReShelf is powered by Virtual Reality games engines that generate interactive digital 3D models of each SKU which are then used as the data to identify when a product is Out-Of-Stock.

Using these virtual 3D models of supermarket products in this way, to train AI-powered computer vision algorithms to carry out SKU-level detections, is a groundbreaking new approach to On-Shelf Availability.

Synthetic Computer Vision software like Neurolabs’ ReShelf makes the on-shelf product detection process faster, more cost-effective, and truly scalable when compared to other automation solutions.

A virtual 3D Stock-Keeping Unit used for Synthetic Computer Vision
A virtual 3D Stock-Keeping Unit used for Synthetic Computer Vision. (GIF by author)

A Flexible Solution

Due to the fact that the data used to train Neurolabs’ computer vision models is synthetic, ReShelf does not require the manual effort of retraining the AI model with new images of a product every time the packaging changes.

Instead of the time-consuming practice of gathering new real data, the use of synthetically generated data (in this case the easy-changeable 3D model of a supermarket product) means the process is radically faster. The result is a solution that can recognise product changes before they even hit the shelves.

an example of typical packaging changes to a supermarket product
Synthetic Computer Vision easily adapts to product changes so interruptions to shelf monitoring are avoided. (Image by Author)

Beyond Inventory Visibility

Neurolabs isn’t stopping at On-Shelf Availability and Planogram Compliance. Their collaboration with UiPath unleashes the best of Synthetic Computer Vision and Robotic Process Automation that enables a holistic approach to inventory automation for retailers.

This helps them get to the root of the inventory problem in a retailer’s supply chain. It also provides them with true flexibility in terms of transforming the shelf insights they collect into a wide array of rapid and impactful actions for the retailer.

This is due to the ease of implementation with the majority of retail IT systems that UiPath’s automation software provides.

The ability to simply automate visual-based tasks by combining Neurolabs’ Synthetic Computer Vision software with UiPath’s automation technology means that you don’t have to stop at in-store optimisation. In fact, this approach can easily be applied to the automation of each stage of a consumer packaged good’s journey, from manufacturing and distribution, to checkout, recycling, and much more.

The Necessity for Visual-Based Automation

With the rising costs of labour combined with the increasing demands of consumers, automation is now becoming a necessity for the top supermarkets to stay competitive.

The good thing is that the technology has reached a tipping point and today you can easily access world class automation with truly compelling economies of scale.

The traditional approach to On-Shelf Availability has resulted in an average Out-of-Stock rate of 8%, meaning one out of every 13 products is not available for sale when a consumer wants it. This rate rises further to 10%+ for discounted products.

With this reality in mind, it’s clear that a large opportunity exists for those who are willing to innovate with a more sophisticated and capable solution to staff-intensive visual-based work.

The question then is not whether to implement automation technology, such as SCV, into your in-store operations but when to do it.

A virtual recreation of a real world supermarket shelf for Synthetic Computer Vision
Both the supermarket environment and each product can be easily digitised to improve on-shelf detections. (GIF by author)

The Time for Retail Automation is Now

Today, 5% of all sales are lost due to Out-Of-Stocks, with, on average, 8% of SKUs remaining Out-Of-Stock. The biggest headache here is that the issue simply does not have to exist with the right use of technology.

Neurolabs’ is helping put an end to retail inefficiency and helping supermarkets thrive in an increasingly competitive landscape with the savvy use of visual-based automation technology.

The most innovative retailers like Auchan are taking action now by turning their in-store inventory problem into a clear competitive advantage that pleases both customers and staff alike.

Retailers who embrace the future of retail technology in this way aren’t just adapting to survive, they are ensuring a future in which their retail business thrives.

Instant shelf detections using Synthetic Computer Vision means store staff are always aware of availability. (GIF by author)

Written by Luke Hallinan, Product Marketing Manager at Neurolabs.

Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. 🤯

Neurolabs helps puts an end to Out-Of-Stocks using a powerful combination of computer vision and synthetic data, improving customer experience and increasing revenue. 🤖 🛒

--

--

--

We help retailers automate time-consuming and costly business processes using Synthetic Computer Vision.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

The Walmart Content Marketing Strategy: How to increase high-intent organic traffic to your website

Ché Wijesinghe of Cape Privacy: 5 Things You Need To Know To Optimize Your Company’s Approach to…

The # 1 Step For Taking Your Offline Business Online!

Thrive Digitally in a Mobile Future

Why does your small business need a website?

Elements Global Services vs. iWorkGlobal: Which Global Expansion Platform is Better?

Have we reached ‘Peak Drone’​?

When the retail crisis becomes a cultural crisis

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Neurolabs

Neurolabs

We help retailers automate time-consuming and costly business processes using Synthetic Computer Vision.

More from Medium

Natural Language Processing Challenges

NLP Shorts — Subword Tokenizers

An overview of alignment models

NLP Corpus Consistency and Accuracy