Multi dimensional audience segmentations in products
summary
Yango Delivery combines behavioral, geographic and ML signals to produce usable segments: classic RFM and an NPS+value map, an ML scoring feed that selects users above ~40% relevance for cross‑sell, and geo triggers (hardware‑store taxi routes) that lift cargo orders 14%. Churn prediction models use a user’s median frequency interval and counted skipped intervals to estimate return probability, then apply thresholds (green >20% return, black <10%) to decide when to trigger re‑engagement.
AI-written summary · about
chapters (10)
- 0:00Multi-dimensional segmentation intro
- 3:21Why segmentation is needed
- 6:52Segmentation model types
- 8:16Multi-dimensional examples
- 13:46ML scoring for prediction
- 21:58Geo segmentation for cargo
- 25:13Churn prediction with intervals
- 36:23Churn thresholds setting
- 43:16Summary and benefits
- 44:39Q&A
related talks
29mUser Motivation: Refining Customer Segments with Location
34mOptimizing E-commerce: Data Science for Better CX & Sales
13mOptimizing Subscription Services with Uplift Modeling
27mUnlocking Product Growth With Big Data, Data Science And Machine Learning
48mHow to Use Analytics to Optimize Your Product
21mData Analytics for Better Product Decision Making
20mMaximizing monetization via cross-category affinities
43mRecommendation Systems in Market Research