AI-Driven Store Shelves and Planogram Assessment

This is a paid opportunity. In order to be eligible to apply for this project, you need to be part of the Omdena community and have finished at least one AI Innovation Challenge.

You can find our upcoming AI Innovation Challenges at https://omdena.com/projects. 

The problem

The current method of conducting shelf audits in retail stores presents considerable challenges for manufacturers and distributors. Field teams spend a significant amount of time visiting stores to gather information about inventory levels, shelf share, and planogram compliance. This process is not only time-consuming but also prone to human error, resulting in inaccurate data and potentially flawed business decisions. The lack of real-time insights into shelf conditions hinders agile responses to stockouts, misplaced products, and planogram deviations. These tasks are primarily conducted manually or using outdated systems, which not only slows down the process but also impacts the accuracy and timelines. 

Impact of the Problem:

• Inaccurate Data and Inventory Management Issues: Manual data collection is susceptible to errors, leading to inaccurate inventory counts and stock discrepancies. This can result in lost sales due to stockouts, overstocking of certain products, and inefficient supply chain management.
• Lost Sales and Revenue: Out-of-stock situations and poor product placement can negatively impact sales and revenue. Without real-time visibility into shelf conditions, manufacturers and distributors struggle to optimize product availability and placement, leading to missed sales opportunities.
• Inefficient Field Operations: Manual audits consume valuable time and resources of field teams. This reduces the time available for other critical tasks, such as building relationships with retailers, promoting new products, and gathering market intelligence.
• Difficulty in Measuring Marketing ROI: Without accurate planogram compliance data, it’s difficult to assess the effectiveness of merchandising strategies and measure the return on investment (ROI) of marketing campaigns. Manufacturers struggle to understand if their products are being displayed as intended and if their shelf space is being optimized.

This project aims to transform the retail shelf monitoring process by developing an AI-powered solution that automates data collection and analysis. The goal is to create a reliable system that can accurately identify SKUs, assess shelf share, and verify planogram compliance using image-matching technology. By automating these key tasks, manufacturers and distributors can gain real-time insights into shelf conditions, optimize product availability and placement, and improve the efficiency of their field operations. This initiative promises to modernize retail execution strategies, enabling data-driven decision-making and ultimately driving sales growth and improved relationships with retailers.

The project goals

The primary goal of this project is to develop an AI-powered system that transforms retail shelf auditing for manufacturers and distributors. By integrating image-matching technology and AI algorithms, the system aims to automate key processes like SKU identification, shelf share analysis, and planogram compliance verification, facilitating data-driven decisions with improved accuracy and speed. This initiative will unfold over a series of planned phases, each aimed at optimizing the shelf auditing workflow and enhancing the capacity to respond to real-time retail conditions:

1. SKU Image Database Curation and System Architecture Design: The initial phase involves curating a comprehensive SKU image database and designing the system architecture. This will allow to establish a foundation for visual product recognition..
2. Development of the Core Image Matching Engine: This phase focuses on creating the AI models and API endpoints that will allow the system to identify SKUs from captured images and return relevant product information.
3. Pilot Stock Presence and Shelf Share Analysis: Implement and test the stock presence and shelf share analysis algorithms, this will allow validate the accuracy and effectiveness of the model designed.
4. Missing SKU Detection and Alert System Integration: This phase focuses on developing AI models to identify out-of-stock SKUs and trigger alerts to relevant stakeholders, enabling rapid replenishment and minimizing lost sales.
5. Planogram Compliance Module Development and Testing: Develop and test the planogram compliance module, to compare captured shelf images against predefined planograms.

Thus, this project aims to deliver an advanced AI-driven solution that revolutionizes the way retail shelf monitoring is conducted. By leveraging cutting-edge technology and AI, this initiative is expected to transform retail execution strategies, leading to more timely, accurate, and effective inventory management, improved sales performance, and stronger relationships with retailers. This strategic approach will result in substantial benefits in operational efficiency and revenue growth, contributing to a more responsive and data-driven approach to retail execution.

**More details will be shared with the designated team.

Why join? The uniqueness of Omdena Top Talent Projects

Top Talent opportunities come as a natural next step after participating in Omdena’s AI Innovation Challenges.

Everyone in the community is eligible to participate once they have shown the relevant skills based on the merit of involvement in past Omdena challenges and the community.

If you are looking for the next challenge after participating in one or more Omdena AI Innovation Challenges, then we believe you have made the right choice! With a healthy, pressured environment, you will be pushed to contribute, learn and grow even more.

Find more information on how an Omdena Top Talent Program works