eBay appears to be testing a "Find Similar" feature in search for both mobile app and desktop experiences.
Users have noticed the addition of three vertical dots at the bottom right of results in search and clicking those dots pops up an option to "view similar active items."
Currently, we're seeing this feature showing in Chrome incognito but not when logged in, in Firefox logged in but not incognito and when logged in on the latest version of the Android app, suggesting eBay may be doing A/B testing or a phased rollout and it may not be visible to all users at this time.
Interestingly, the "view similar active items" option appears to simply copy the title of the listing into a new search window, suggesting eBay is not using their image recognition technology to make the match.
If you use the option on a listing with a much more generic title, the results are similarly more generic and less closely matched to the original item.
A buyer would likely get the same results by simply copying and pasting the title of an item they are looking at into the search bar themselves, which could be a workaround for users who say the "find similar" functionality is only intermittently available or has disappeared.
Since the most recent update, the “find similar” feature when looking at items if no longer there. Anyone know how to make it come back?? It was very useful for comparing prices.
I was using eBay a few days ago and all of a sudden, the see similar tab disappeared. I can’t find anything online about it, other than sellers hated the tab because it allowed buyers to find the least expensive item. I called their help desk twice, and they knew nothing about it. I wish someone who knew something more about this would answer your post.
eBay had previously tested a similar functionality within the listing page itself, by overlaying a "find similar" button over seller provided images, which angered sellers who felt it was unfair for eBay to use their images to direct buyers to competitor listings.
They had also previously teased adding something similar to search in March 2023, saying it would improve search and browse by enabling a kind of digital "window shopping" for buyers.
However, at that time eBay had said the feature would be using machine learning and image recognition to help fill in the gaps where text based search may fail to capture what buyers really mean.
A new feature generates customer delight by using modern computer vision techniques to drive new search paradigms through visual discovery.
We live in a world of discovery where visual appetite reigns supreme. Window shopping, infinite scroll lists, and micro engagements using simple visual cues are the norm. Search engines traditionally interpret a textual query input and match items and/or documents ranked by their relevance to the input query. The relevance of the retrieved results is based on scoring the closeness of the input query to the matching items/documents.
This traditional approach heavily constrains the user to provide a language-bounded interpretation of their implicit preferences such as style and aesthetic feel, which are not usually available in a shared vocabulary. Bridging this gap between inspiration and discovery by enabling visual first pivots in search is the goal of our work.
Let’s illustrate this with an example. A user has an ethnic Turkish themed living room and is looking to purchase pillows for their recently purchased butterscotch-colored couch. In tune with their personal style, the user starts off their search using “turkish throw pillow,” reviews the results and in the process identifies the specific pattern used in pillows from Turkey as “kilim.”
They attempt to search for this pillow using various combinations of textual queries such as “orange kilim pillows,” “orange throw kilim pillows” or even a broad search “kilim pillows” which does not yield their desired result in the top results.
Though the results were highly relevant and had the best match with the query text which has been provided, the result of matching items varies significantly for each of these queries, as all of the inventory is not being displayed, forcing the user to query over and over again to try and get the correct combination of query text. Thus, words fail to elicit the style preference that the buyer has intended to search for.
In such situations, we need to provide capabilities to help engage enthusiast customers by inviting them to browse their assortment in a more visually appealing methodologies allowing them to zero down on the item they love.
So why does it appear eBay has abandoned image recognition to find "visually similar" results for this feature, instead sticking to text based query matching they have admitted sometimes fails to elicit the best results?
eBay has had an image based search option in the mobile app since 2017, so this should not be a new or innovative technology.
However, it was removed from the app for several months in 2021 because there were "inconsistencies" and when they finally re-enabled search by image months later, the results were even less useful than before, often failing to identify truly relevant or similar items in search.
For example, previously testing image search in 2022 with a mousepad brought up glass sculptures and vases that were not even vaguely related.
More recent testing in 2023 shows not much progress has been made - while manatees do love to hang out around the warm water near power plants here in Florida, in 20+ years, we've yet to see one turn into Godzilla. 😉
The results of the "view similar" test on listing pages also revealed that eBay's AI/machine learning image recognition technology may not be quite ready for prime time.
In many examples, while the general category was similar to what the buyer was looking at, the actual visual similarity was not even close.
The fact that this latest test of "find similar" in search appears to have abandoned image recognition all together in favor of a simple text based search does not bode well for CEO Jamie Iannone's "magical" tech-led reimagination of the platform or the idea that sellers will be able to use AI to create listings using only an image any time soon.