Beyond Propensity: From traditional ML to Uplift Modelling

Given the vast amounts of data that marketers now have on their customers, it’s no surprise that many are looking to optimise their marketing spend and devise more effective personalisation strategies with machine learning (ML). Propensity models are some of the most widely used ML approaches in marketing. These tools are used to make predictions using historical data, but when it comes to informing marketing tactics they often fail to perform – sometimes in ways that can have significant impacts on cost and brand reputation. In this tech talk, Faculty’s Lead Data Scientist for Consumer Business, Gary Willis, will discuss use cases and applications of ML for marketing, including: - Places where standard ML approaches like propensity models work … and where they fall down. - Why tackling some of the most important problems in marketing requires more than just adding more data. - How a set of causal methods known as “uplift models” are quickly becoming more mainstream for modelling consumer behaviour and improving marketing impact.