17. Image-based Recommendations
Image recommendation deals with finding the most similar objects for a given object where the object is present in the form of an image.
What can designers do with this pattern?
Some online shops such as Amazon and AliExpress, and search engines such as Google are using this to provide the user with similar items based on an image
Input or output?
How do users control the algorithm?
By uploading an image and tweak some parameters (such as size, dominant color, type of image).
How do users understand the control?
The user will get an overview of the items based on the image in the form of a list or grid.
Some examples of use
Please let us know if you have a related reference with the scientific research.
- McAuley, J., Targett, C., Shi, Q., & Van Den Hengel, A. (2015, August). Image-based recommendations on styles and substitutes. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval (pp. 43-52).
Comments & Talks
React on this algoritmic affordance and get in touch with the publisher over this algoritmic affordance Koen van Turnhout.
Related algoritmic affordance pattern in this library are listed below.