Causal Inference in Python: Applying Causal Inference in the Tech Industry 1st Edition

“How many customers would an extra dollar of internet advertising generate? Which clients will only make a purchase if they have a discount coupon? How can the best pricing plan be established? Causal inference is the most effective method for figuring out how the levers at our disposal impact the business KPIs we wish to influence. Matheus Facure, a senior data scientist at Nubank and the author of this book, describes the mostly unrealized potential of causal inference for impact and effect estimation. Classical causal inference techniques such as randomized control trials (A/B tests), linear regression, propensity score, synthetic controls, and difference-in-differences will be taught to managers, data scientists, and business analysts. Every technique has an industry application to provide a foundational example.