Are you running various almost-identical creatives on different ad campaigns and channels at once? If so, we bet you’d like to see creative performance data for some of these creatives in collective groups rather than individually. With Creative Clustering, Singular utilizes a different kind of algorithm to ensure you’re seeing data that reflects the set of creatives you’re most interested. Whether the differences between your images are intentional or unintentional, we’re able to group those creatives within a common theme to give you a better picture of your creative performance.

How do we do it? For slightly different images, a Pixel-Perfect match isn’t going to be an effective means of grouping. By using an algorithm called Perceptual Image Hashing, we are able to group similar images effectively, giving you the chance to see performance for all your similar-but-slightly-tweaked ad creatives. To learn how we accomplish Creative Clustering, read more here.

Found this interesting? Looking for a career? Singular is hiring!

This post was written by Nir Solomon, Senior Software Engineer at Singular. If you have any questions or feedback, please contact Nir at

Please tap or click “♥︎” to help to promote this story to others.