Work & case studies · SaaS & Technology
NLP for customer feedback analysis
Topic, sentiment and urgency models over reviews and tickets, feeding a weekly voice-of-customer report.
50k+
reviews and tickets classified per month
Weekly
automated voice-of-customer report
Challenge
Product managers were reading a sample of reviews and guessing at trends. Urgent issues surfaced late.
What we built
- Fine-tuned transformer classifiers for topic and sentiment, plus an urgency detector for churn-risk language.
- A pipeline that ingests app-store reviews, support tickets and NPS comments daily.
- A dashboard and automated weekly report highlighting movers, emerging topics and representative quotes.
Results
Every piece of feedback is now categorised, and the product team gets a consistent weekly read on what customers care about, with urgent issues flagged the same day.
Next case study
RAG knowledge base for an enterprise services firm
Ready to chart your AI course?
A free 30-minute consultation: we listen, ask hard questions and tell you honestly where AI will and won't help.