Lucas and Luna dive into synthetic control methods, a causal inference technique that data scientists use when A/B testing is impossible. They walk through a concrete example: how a mid-sized retailer used synthetic controls to measure the revenue impact of opening a new physical store, using a weighted combination of similar stores as a counterfactual. Lucas explains the math behind the method—matching on pre-treatment trends and minimizing a distance metric—while Luna presses on practical pitfalls like the risk of interpolation bias and the importance of a donor pool that wasn't affected by the intervention. They also touch on how companies like Google and Uber have applied synthetic controls in settings from ad effectiveness to marketplace changes. The episode closes with a forward-looking question about whether synthetic controls will become a standard tool in every data scientist's causal inference toolkit.

#SyntheticControl #CausalInference #DataScience #A-BTesting #Counterfactual #RetailAnalytics #BusinessImpact #Google #Uber #DonorPool #InterpolationBias #ExperimentalDesign #MachineLearning #Statistics #Technology #FexingoBusiness #BusinessPodcast #DataDrivenDecisions

Keep every episode free: buymeacoffee.com/fexingo