Unlocking Product Growth With Big Data, Data Science And Machine Learning
summary
Shows concrete practices: use funnel and segmentation analysis to find where customers drop off, run A/B experiments with calculated sample sizes (n ≈ 16·(α/Δ)^2 and typical two‑month runs accounting for seasonality), and measure revenue and engagement tradeoffs. Presents machine learning use cases—machine learning for ranking and recommendations—including regression to forecast support volume, clustering for content tagging, anomaly detection for fraud, and a deployed model that flags buggy C# lines in Visual Studio with about a 60% detection rate.
AI-written summary · about
chapters (12)
- 0:00Introduction and setup
- 1:04How products leverage data
- 3:33Role of product managers with data
- 4:56Funnel analysis in products
- 7:00Segmentation analysis explained
- 8:46Engagement metrics by product type
- 10:44A/B experimentation fundamentals
- 15:19Designing A/B experiments
- 20:12Introduction to machine learning
- 21:35Personalization with machine learning
- 22:59Machine learning applications
- 24:55Q&A and closing remarks
related talks
56mMachine Learning in E‑commerce
23mDelivering business success with AI
32mAn Only One Step Ahead Guide for Machine Learning Projects
21mData Analytics for Better Product Decision Making
27mA Look Inside Applied Machine Learning
53mMachine Learning in E‑commerce
49mThe Analytics of Growth Hacking
22mReal-world applications of machine learning: Beyond the hype