Ozon has developed its own product card moderation system based on machine learning methods, a company representative told RB.RU. The system automates the verification of new positions and reduces card processing time by 10 times.

Ozon Deploys Machine Learning Technologies for Accelerated Product Moderation

The innovation will speed up the placement of sellers’ products on the site: the speed of automatic verification will average three minutes. This is noted to be 10 times faster than manual moderation.

The system automatically checks product cards when uploading and analyzes possible violations in the description and photo. If a problem is identified, the product is not allowed on the market or is sent for manual verification.

The new moderation system uses machine learning (ML) methods: the algorithm is trained on the accumulated matrix of decisions of Ozon moderators and blocked cards, for which violations were previously detected.

The moderation technology was developed by Ozon Tech’s own IT team and is gradually being introduced into the business processes of the market.

According to Ozon’s own data, merchants list more than 1 million new product items on the marketplace every day, and more than 20% of them are already under automatic moderation.

Author:

anastasia mariana

Source: RB

Previous articleImages from 30 years ago reveal volcanic activity on Venus
Next articleIn 2022, the number of companies opened by Russians in Turkey increased by 670%
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.

LEAVE A REPLY

Please enter your comment!
Please enter your name here