Updated: 6 days ago
In early 2020, Neurolabs helped Spanish supermarket group UVESCO keep its shelves stocked and increase long term sales.
UVESCO is a leading group in the mass consumption and food distribution sector, in the process of expansion, with more than 240 supermarket stores.
Empty shelves are bad news for retailers. A lack of stock, under-ordering, late deliveries, and food spoilage all cut into profits.
These existing challenges, faced by FMCG businesses, were made even more complicated by Covid-19. The pandemic saw retailers like UVESCO struggling to navigate distribution crises and unprecedented fluctuations in demand. Neurolabs' object detection and on-shelf product monitoring technology provided UVESCO with invaluable insights into its front-of-store inventory, helping the store comply with its planogram by revealing stock issues in real-time. The software also identified patterns in consumer shopping behaviour and distributor performance, empowering the company to quantify missed opportunity costs and identify ways to improve the merchandising process.
Identifying the gaps
Using an algorithm and a network of cameras, our 'Computer Vision' (CV) models can visually interpret images in several ways. For retailers, Neurolabs technology can quickly identify common shelf issues through a process of deep learning.
Using product recognition software, Neurolabs continuously monitored various shelf areas throughout the day and gave UVESCO in-depth insights into their front-of-store product availability. The goals were twofold: To prevent poorly stocked shelves and to measure the impact of consistent CV shelf monitoring.
The data also helped UVESCO to identify which products sold out most frequently and at which times, enabling the retailer to prepare for surges and dips in demand so that they could ensure fully stocked shelves and increase sales.
Using a similar approach, Neurolabs helped UVESCO monitor distributor performance to determine and address the root cause of stock shortages.
The importance of moving quickly
With no need for image gathering, data labelling, or coding, Neurolabs can roll out object recognition technology at pace. The CV monitoring system takes little time to set up, and the learning software uses synthetic data, meaning retailers can start using the technology almost immediately after installation.
That was critical at the height of the Covid-19 pandemic. Without the need to collect significant amounts of data in person, the project could get up-to-speed with limited store visits from Neurolabs employees. The timing of the project gave UVESCO an insight into on-shelf product availability when they most needed it. With real-time shelf monitoring in place, the supermarket was much better equipped to weather the challenge of fluctuating customer demands.
Speaking of the collaboration with UVESCO, Remus Pop, Neurolabs Co-founder, said:
"Given the challenges of the pandemic, it was important to roll out our product identification and monitoring software as quickly as possible. We were conscious that a delay in the project would mean a missed opportunity to measure our solution's impact."
"Because our technology uses synthetic data, we can generate detailed product recognition models much more quickly than the traditional approach, without relying on the time-consuming and expensive process of real store item image gathering and labelling." Remus Pop, Co-Founder & COO at Neurolabs
"That allowed us to support UVESCO during a challenging time and paved the way for meaningful changes in the long-term."
Over four months, Neurolabs helped UVESCO gain invaluable insights into consumer shopping and distributor shelf fulfilment behaviour. Some of the insights included were:
Average shelf capacity
Percentage of the time shelves are full
Percentage of the time distributors deliver on time
Estimates of missed sales opportunities
Top products with availability inefficiencie
For Chris Burleigh, Head of Digital Transformation and Innovation at GRUPO UVESCO, the collaboration was a success:
"Thanks to the computer vision technology that Neurolabs provided, we were able to monitor the store shelves closely. This increased the visibility and awareness of what was happening in our shops in real-time." Chris Burleigh, Head of Digital Transformation & Innovation GRUPO UVESCO
“We would call this project a success. For the first time, we’ve been able to quantify the extent of inventory inefficiencies and learn lessons that will help us improve our processes. It’s a great first step and we are looking forward to extending the analysis to other stores and regions.”
Following the project’s success, UVESCO decided to further expand the technology’s deployment to multiple stores across various locations in the Basque Country. The expansion started in April 2021.
Post Covid-19, it is anticipated that there will be an increased reliance on automated solutions such as CV technology to tackle the On-Shelf Availability (OSA) and Out Of Stock (OSS) challenge.
Neurolabs’ object recognition software can maximise efficiency not only for single stores but for entire retail networks.
The CV technology can be set up in warehouses to monitor stock levels, while in-store monitoring can alert businesses when additional supplies are needed.
By automating the inventory management process, retail businesses can expect to see improved results from their supply chains and ultimately, greater profits.
Would you like to know how Neurolabs can help your business implement computer vision technology? Contact the Neurolabs team now.
The company’s vision is simple: democratise Computer Vision by breaking down the barriers to adoption. Neurolabs substitutes the expensive and rare real-world data required to train Computer Vision algorithms, with synthetically generated data to provide massive, rich and diverse low-cost datasets at a fraction of the cost and time. Its Computer Vision technology, propelled by a synthetic data generation engine, enables rapid state-of-the-art development of object recognition solutions across multiple use cases and industries, accelerating the automation of repetitive visual tasks. For more information visit www.neurolabs.ai.