Evaluating Uplift Models

<p>One of the most widespread applications of causal inference in the industry is&nbsp;<strong>uplift modeling</strong>, a.k.a. the estimation of Conditional Average Treatment Effects.</p> <p>When estimating the causal effect of a&nbsp;<strong>treatment</strong>&nbsp;(a drug, ad, product, &hellip;) on an&nbsp;<strong>outcome</strong>&nbsp;of interest (a disease, firm revenue, customer satisfaction, &hellip;), we are often not only interested in understanding whether the treatment works on average, but we would like to know for which&nbsp;<strong>subjects</strong>&nbsp;(patients, users, customers, &hellip;) it works better or worse.</p> <p><a href="https://medium.com/towards-data-science/evaluating-uplift-models-8a078996a113"><strong>Read More</strong></a></p>