Recommendation SystemConsumer FacingVerified
Reviewed and published by trentmaziarz, March 18, 2026. Discovered and drafted by our automated research pipeline.
Shutterstock uses a custom-built neural network to power visual similarity search and reverse image search across its entire library, allowing users to find matching content by uploading a photo rather than typing keywords. This applies to both images and video.
Details
Shutterstock launched reverse image search and visually similar search in March 2016, powered by a custom-built convolutional neural network that analyzes pixel data rather than metadata. The system has been continuously expanded: it now covers images, video, and is exposed via a developer API. Shutterstock later extended the neural network to video, allowing users to upload a photo or frame and receive video clips matching its visual composition, light temperature, and subject matter.
Products affected
Shutterstock
Sources & Evidence
Company Disclosure
Other practices by Shutterstock
Data AnalysisThrough its 2021 acquisition of three AI companies under the Shutterstock.AI subsidiary (Pattern89, Datasine, and Shotzr), Shutterstock offers AI tools that analyze the visual and compositional elements of ad creatives and predict their performance before a campaign goes live.ModerationShutterstock uses automated AI systems to flag and filter offensive, adult, or policy-violating content from its contributor-submitted library and from AI-generated outputs on its platform. These safeguards also include multi-layered controls to prevent generation of harmful content via its AI tools.OtherIn October 2025, Shutterstock launched a formal B2B suite of "AI Services" that go beyond simply licensing content — offering specialized dataset curation, human aesthetic preference labeling (RLHF-style), annotation, and model evaluation pipelines to AI developers building new models.
Have evidence about Shutterstock's AI practices? Submit a report.
Report a Sighting →