Large IT corporation
Achieved more reliable sentiment analysis
without investing in model infrastructure
Accelerate your
e-commerce AI
Accelerate your
e-commerce AI
Client
Large IT corporationChallenge
Ramp up sentiment analysis of social media mentions. Manual sentiment annotation was limited to 2.6K/day.Solution
Toloka's Adaptive ML Models combine autolabeling with manual labeling for reliable social media monitoring.Total volume: 60K labels/day.
Business impact
20x increase in volume with new human-in-the-loop process- 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.
