Understanding User Behaviour with Uplift Models
At Monzo, we continuously run A/B tests to provide the best user experience to our customers. We test out different designs to marketing campaigns that make a user more likely to interact with us. As part of this, we often ask ourselves: Who are the types of users that respond to our experiment? To answer this, we can build uplift models that allow us to estimate the causal effect of what we're treating. During this presentation, we'll go through the steps to build and validate this.
Valeria recently joined Monzo Bank as Senior Data Scientist. Previously, she worked on the development of Machine Learning solutions for different business areas of Lloyds Banking Group and their customers. During this time, she focused on building tools and processes to detect and mitigate bias in Machine Learning models. Before joining LBG, Valeria started her career in Cambridge researching on the economics of privacy at Microsoft Research and working for TAB, a Fintech startup. Valeria is a strong advocate of ethics and responsibility in AI as well as bringing more diversity into tech teams.