Accelerate your
e-commerce AI
Accelerate your
e-commerce AI
Client
Large IT corporationChallenge
Optimize the process for classifying social media mentions as spam/feedback/neutral/news. The client was handling 36K items per day with an outdated model and sending an additional 19K items per day to Toloka for manual labeling.Solution
A human-in-the-loop workflow using Toloka's Adaptive ML Models was used to train an accurate model. With improved accuracy using the new model, manual labeling was reduced from 19K to 9K items per day.Business impact
- 95% of messages labeled within 3 seconds
- 5X reduction in average cost per label
- Stable quality at approximately 75%
Similar success stories
- Trained a voice assistant with language dataTrained a voice assistant with language datax5accuracy in the new languages
- tech
- data collection
- Set up a moderation process for items on sale to ensure legal and cultural complianceSet up a moderation process for items on sale to ensure legal and cultural compliance50%reduced cost per item with x500 more items verified daily
- E-commerce
- Moderation
- Improved crowdsourced translations of product descriptionsImproved crowdsourced translations of product descriptions17%budget reduction while achieving optimal quality
- E-commerce
- Product catalog
- Improved the accuracy of a predictive tool using local shopping patternsImproved the accuracy of a predictive tool using local shopping patterns30%improvement in app accuracy after data collection, reaching 95%
- E-commerce
- offline
Accelerate your e-commerce AI
Let's talk about the ideal solution for your data needs.
