Optimizing E-commerce: Data Science for Better CX & Sales
summary
Shows RFM and cohort workflows with actual math: recency, frequency, monetary multiplied into a 12-point score example (12 months / 6 active = 60% consistency, score 12) used to move customers up one tier. Describes integrating scores with email marketing, building a transaction‑based credit score for a smart wallet, launching a model to production in five weeks, and iterating with customers while working toward explainable forecasting and recommendation systems and A/B testing to lift conversion.
AI-written summary · about
chapters (7)
- 0:00Optimizing e-commerce with data science
- 4:00Customer segments in e-commerce
- 16:36RFM analysis for segmentation
- 24:45Data governance challenges
- 26:11Data science director role
- 30:52Explainable forecasting models
- 33:17Collaborative model improvement
related talks
28mCrafting Hyper-Relevant User Experiences
27mUnlocking Product Growth With Big Data, Data Science And Machine Learning
21mData Analytics for Better Product Decision Making
28mThe Value of UX Applied to Company Data
36mThe Future of Traditional Shopping Driven by Customer Centric Approaches by Santiago Cabrera Naranjo
44mSituationalization: Using situational data to optimize online shops
41mMarketing Data Science
27mOptimizing Omnichannel Order Fulfillment with AI and Advanced Analytics