Machine Learning for All
summary
Claims a concrete outcome: classifies message intent by job function and seniority to surface leads that need human follow up. Implementation uses keyword frequency and tag-based text analysis feeding a pipeline built on common open-source libraries and models. The project moves from prototype to a productized ML pipeline at SalesLoft that runs on real customer data, integrates with existing workflows, and materially changes routing and prioritization rather than just illustrating concepts.
AI-written summary · about
chapters (8)
- 0:00Welcome
- 1:31Why ML matters today
- 2:57ML in daily life
- 4:37How machine learning powers personalization
- 6:45ML in everyday systems
- 8:12Making ML accessible
- 13:52Foundational concepts
- 14:36Beginner ML projects
related talks
39mDeveloping Machine Learning for Impact
32mHarnessing Large Language Models for Enhanced Customer Experience
21mBuilding Scalable ML Systems: Strategies and Insights
29mEngineering Machine Learning Technologies
32mHow to Machine Learn-ify any Product
33mImpact of NLP in AI-powered Bank
46mDeveloping Machine Learning Algorithms in LUN Projects
32mLiveMLP: ML Platform for Assisting Contact Center Agents in Real-Time