Beyond Surveys: Real-Time User Satisfaction Prediction
summary
A system called DNPS predicts session-level Net Promoter Score from telemetry, behavior and text using a hybrid stack of gradient-boosted trees, sequence models and BERT embeddings, fused with an explainability layer (SHAP/LIME). It claims 85.9% accuracy with MAE ≈ 1.21 and live inference at ~80 ms latency. Ablations show removing text drops accuracy to ≈55% and removing behavioral/telemetry drops it to ≈78%, and dashboards surface root causes like high back‑clicks and short sessions.
AI-written summary · about
chapters (15)
- 0:00Intro: Beyond Surveys—Real‑Time NPS Prediction with LLMs + Telemetry
- 0:39NPS 101: What Net Promoter Score Measures
- 1:16How NPS Is Calculated (Detractors, Passives, Promoters)
- 2:10How Companies Collect NPS Today (and Why It’s Slow)
- 2:49The 4 Big Problems with Traditional NPS Surveys
- 3:52The Big Idea: Predict Sentiment Without Surveys
- 4:14Introducing DNPS: Dynamic Net Promoter Score
- 4:45DNPS Architecture Overview: Ingestion → AI Engine → Insights
- 4:56Data Collection: Behavior, Telemetry, and Text Feedback
- 6:06Data Processing Pipeline: Cleaning, Alignment, Feature Extraction
- 6:57Hybrid Modeling: Structured + Sequence + Text Models
- 8:34Fusion Layer + Explainable AI (SHAP/LIME)
- 10:01Results: Accuracy, Ablation Study, and Real‑Time Latency
- 10:59Key Drivers & Business Value from Explainability Insights
- 11:45Limitations, Future Work, and Closing
related talks
33mPredictive NPS (PNPS)
38mUsing Recurrent Neuronal Networks for Customer Predictions
30mPerforming Content: Can NLP and Deep Learning algorithms predict reader prefere...
23mHyper-personalisation fueled by psychometrics: The ultimate power-up for retention and monetisation
24mScaling on Satisfaction: Automated Rollouts Driven by User Feedback - Thomas Vitale & Whitney Lee
26mImproving customer experience through journey...
32mHow to be best in conveying the message by using NLP approach (Big Five modeling)
22mUsing Machine Learning to Improve UI/UX
