How Data Scientists Estimate Causal Effects with Double Machine Learning
from The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations Hosted by Fexingo
Episode 57 of The Data Science Podcast dives into double machine learning (DML), a technique that estimates causal effects from observational data without assuming a linear model. Lucas and Luna walk through a real-world example: a health-tech startup using DML to determine whether a new wellness program reduces employee churn. They explain why traditional regression falls short, how DML combines machine learning with orthogonalization to remove bias, and what data scientists need to watch for when applying it. The episode also touches on the practical trade-offs between DML and other causal inference methods like instrumental variables and synthetic controls. By the end, listeners understand when to reach for DML and what pitfalls to avoid. The episode closes with a reflection on how causal inference is becoming a core competency for data scientists across industries. #DataScience #CausalInference #DoubleMachineLearning #MachineLearning #ObservationalData #TreatmentEffect #Confounding #Orthogonalization #NeymanOrthogonality #Chernozhukov #CrossFitting #ATE #CATE #HTE #StartupAnalytics #EmployeeChurn #Technology #FexingoBusiness Keep every episode free: buymeacoffee.com/fexingo
Embed this episode
No transcript yet.