Data Science Driven Business Insights with Python and PySp
summary
Python on Bluemix plus PySpark and DashDB run a production pipeline that cleans web and offline logs, trains over 80 model variations, and deploys scoring and automation to sales and marketing. Churn prediction uses AFT survival regression at scale; recommendations use ALS with implicit feedback and percentile ranking. A diagnostic change to landing pages and keywords yields a measurable 10% increase in conversions, and periodic retraining updates models as usage shifts.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 10:46Data science team and IBM’s architecture
- 24:23Apache Spark for data scientists
- 44:54Churn analytics with survival regression
- 1:04:54Recommendation engines with Spark ML
- 1:39:49PySpark notebook tutorial
- 1:59:25Q&A
related talks
21mData-driven approaches in a technology startup
42mHow mobile.de brings Data Science to Production...
51mSpotlight on Emerging Data Science Worskspaces and Spark as Development Levers
26mLarge-Scale Recommendation System with Python and Spark
29mAI-Driven Business Success: Measurable Results and Revolutionized Sales
24mSmart approach in development and deployment process for ML models
01h 39mApplying Rigorous Machine Learning Methods in Business Strategy
33mYour best Bet: Effortless MLOps with Python Models in