The Impact of Machine Learning in Companies
summary
Describes applying machine learning as an engineering practice in business, with a one-year pilot to measure TV ad impact using online signals. The project instruments websites, cleans and labels noisy web logs to create features, then builds models for anomaly detection and A/B-style causal comparisons (including feature transforms like temperature deltas) and an optimization loop to choose ad slots; prototypes are integrated with dev teams and deployed to produce actionable insights.
AI-written summary · about
chapters (32)
- 0:00Start
- 3:10The Industrial Revolution
- 5:00The Fantasies
- 8:10The 2 Pillars of ML
- 8:35Introduction of François Xavier
- 9:45The Steam Engine
- 14:15The History of Algorithms
- 15:50Lessons from the Software
- 17:00The Signal in the Online World
- 18:30Transmitting Data into Information
- 20:45Modeling Behavior
- 21:45Detecting Anomalies
- 26:15Predictions
- 27:40What is the X9?
- 29:05What is Data Mining?
- 30:00What is Induction?
- 31:30A Machine Much More Human Than We Imagine
- 32:05How to Initiate the Project?
- 32:40The Goal of the Game
- 34:40Innovation
- 35:30Agility
- 36:10What Data?
- 37:00What Knowledge?
- 37:30How to Reformulate?
- 38:50How Does It Work?
- 39:30Concrete Examples
- 40:50The Profession
- 42:45The Friends
- 43:25Enemy Number 1
- 44:40Enemy Number 2
- 45:25Enemy Number 3
- 46:10Conclusion
related talks
39mDeveloping Machine Learning for Impact
37mApplying ML in AdTech and Lifecycle of an ML project
39mMachine Learning Engineering
27mA Look Inside Applied Machine Learning
22mBefore the Model: How Machine Learning Products Start...
22mReal-world applications of machine learning: Beyond the hype
56mMachine Learning in E‑commerce
21mHow The Application Of Machine Learning Is Changing The Way Companies Use Data