The company, a leading retail & classifieds global group, reached out to super.AI to get help with cleaning up its user-generated product tags, with the ultimate goal to enhance the product search and the recommendation engine. We worked with them on a consistent product taxonomy and tagging categories, including for subjective tags such as style, and then process hundreds of thousands of images within a record timeframe. The client is now able to offer much more granular product results and recommendations to its user base and ultimately increase engagement and revenue.
The customer is a multinational Internet group which is known for its principal operations in Internet communication, entertainment, gaming and e-commerce. For one of their e-commerce sites, they wanted to enhance the product search and the recommendation engine. The problem they were facing was that most of the product details (images, description, tags) were provided directly by the users. This resulted in an inconsistent tagging system, with different categories used for the same product types. The resulting models they built using the user-generated tags was therefore based on noisy data, which affected the overall quality of the recommendations offered to the other customers.
When the company contacted us, we started by helping the customer build a consistent product taxonomy. This was important to the overall success of the recommendation engine. We then went on to agree with them on the edge cases: tags for subjective categories such as style. Once there was full alignment on the categories used and we ensured consistency, we transcribed hundreds of thousands of user-generated images with the help of our image transcription data program.
The company was able to tag several hundred thousand images within a record timeframe. The processed data also met their quality thresholds and will be the basis for training a new product recommendation engine with a much higher level of granularity.
“We had a lot of user-generated content and were struggling to make sense of it given the lack of consistency in user-generated tags. Our product recommendation engine was limited in its functionality because of this. Using the super.AI platform has allowed us to define a consistent taxonomy, process hundreds of thousands of images in record time, and significantly enhance our recommendation engine.”