Case Study: Appen improves contributor satisfaction with Provectus AI-powered ticket automation

Appen improves contributor satisfaction by handling over 11K support requests per month with a team of two using ML-driven ticket categorization

Appen, a leading provider of high-quality training data for AI systems, was struggling with a manual contributor support workflow that caused miscategorized tickets, slow handling times, and contributor churn. Provectus helped the company address this challenge by introducing an ML-powered ticket categorization approach integrated with ZenDesk to streamline support operations.

Provectus built a Natural Language Processing solution using TensorFlow and AWS services to automatically categorize, prioritize, and resolve contributor tickets, while routing more complex cases to the support team. The results were significant: around 80% of tickets were resolved automatically, resolution time dropped from two weeks to under 24 hours, and contributor satisfaction increased by 10%, helping Appen scale support with just a two-person team.

Appen