Sometimes, the things we want, simply can’t be described, and when this is the case, we turn to a picture.
Now, with the help of InstantSearch+ innovative technology, you can shop in an entirely new way by beginning your search with an image.
When you don’t know what term to type, or how exactly to describe what you are searching for, you can take a photo on your mobile device and get results that matches that photo.
InstantSearch+ is harnessing the power of AI to help customers easily search for the products they can’t describe but really want.
According to forecasts, by 2020, 6.1 billion people will be searching by images. That means that 6.1 billion people will have access to a smartphone camera on a daily basis. Don’t miss the trend and let your shoppers search however they want to.
No need for any coding or special customization. The Visual Search feature is turned on with a mere change of a switch. Once you turn Visual Search on you will see the camera icon on your site search box and you can go ahead and start searching by images.
As always, InstantSearch+ sophisticated dashboard will show you exactly what images were uploaded to your site, the displayed search results, and how many conversions and revenues did those images yield. You will be able to see how those images impacted your overall conversion rate.
InstantSearchPlus is using a deep learning model in order to create representation of the shopper’s image that will lead to relevant search results. It’s a game changer!
Let’s say that your future shopper is in the physical store at the moment, looking at a piece of furniture they really liked, a colorful patterned sofa, but are not willing to pay the high price in the store, thus turning online to search for what they want. The problem is they can’t really describe that specific piece of furniture, it’s material, shape, pattern etc. A photo search of that exact sofa will probably do the trick. That’s where InstantSearch+ Visual Search feature will come in hand.
InstantSearchPlus is helping shoppers search for what they really want but can’t describe.
InstantSearchPlus Visual Search uses a deep learning model. The model’s output creates a representation of the shopper’s image that can be compared to images of the store’s products listing. That means that the listing images must have the same type of representation or a set of attributes that the AI can match the search image against, similar to metadata.
Once you enable Visual Search on your store, InstantSearchPlus will study all your images and feed them to the AI to create a library of reference points.