Causal Models in Practice at Lyft with Sean Taylor - #486
Analysis
This podcast episode from Practical AI features Sean Taylor, a Staff Data Scientist at Lyft Rideshare Labs. The discussion centers around Taylor's shift to a more hands-on role and the research conducted at Rideshare Labs, which adopts a 'moonshot' approach to problems like forecasting, marketplace experimentation, and decision-making. A significant portion of the episode explores the application of causal models in their work, including the design of forecasting systems, the effectiveness of using business metrics for model development, and the challenges of hierarchical modeling. The episode provides insights into how Lyft is leveraging causal inference in its operations.
Key Takeaways
- •The episode highlights the use of causal models in solving real-world problems at Lyft.
- •It discusses the challenges and benefits of using business metrics for model development.
- •The podcast provides insights into the 'moonshot' approach to research and development.
“The episode explores the role of causality in the work at rideshare labs, including how systems like the aforementioned forecasting system are designed around causal models.”