What it does
The KPI evaluates the visual distinctiveness of packaging in a competitive context on retail shelves. It measures the visual dissimilarity between a designated “critical SKU” and other competitive products within the same category, providing a quantitative basis for assessing brand differentiation and packaging uniqueness.
Case Example: let's say we test a new pack design in our potato range, from brown to red. What is the resulting distinctiveness to our key competitor Lorenz?
Shelf setup:
Result:
While the current setup with the brown design shows relatively high distinctiveness to Lorenz (score: 58), the change to the red design significantly reduces distinctiveness (-11% to 47). The main reason for this change is that Lorenz has many red SKUs in its portfolio. So becoming "more red" makes our brand more similar to Lorenz, reducing distinctiveness.
Why it matters
Distinctive packaging helps a product stand out from the competition on crowded shelves, increasing its visibility and attracting shoppers' attention. However, too much differentiation can lead to a disconnect from the product category, making it difficult for shoppers to understand the product's purpose and positioning. This KPI helps strike the right balance by ensuring a high level of visual distinctiveness that promotes brand recognition without compromising the product's ability to be associated with its category.
How it works
Advanced deep learning models are used to identify all SKUs on a shelf and then measure the visual distinctiveness between the critical SKU and others in the same group. This analysis focuses on ensuring distinctiveness in a competitive context. The output is presented in a tabular format, providing insight into the visual coherence of packaging within each group.
How to achieve great results
- Design packaging elements such as colors, shapes, and images to create a unique visual identity that differentiates the product from the competition.
- Ensure that the packaging remains visually linked to the product category through the use of category-specific cues.
- Introduce bold and innovative packaging designs that break away from category norms while maintaining a clear connection to the product's purpose.
- Experiment with elements such as materials, textures, or package formats to create a distinctive tactile and visual experience for shoppers. Monitor competitor packaging designs to ensure that the product remains visually distinctive over time.
AI models used
This KPI uses state-of-the-art deep learning models, which have been trained on a dataset of millions of images. These models transform SKU images into numerical vectors that enable accurate distinctiveness measurements between products. It also includes a specialized deep learning model trained on millions of annotated SKUs from retail shelves. This model excels at identifying and cataloging each SKU from an uploaded shelf image, ensuring detailed and accurate analysis.
SKU Similarity Matrix
The flip side of distinctiveness is similarity - how similar each pack is to other packs in the shelf. This matrix can be downloaded from the ACE Pack+Shelf app.