Traditional marketing analytics rely on predictive models that estimate the probability of customer behaviours such as churn or purchase. However, these models identify customers who are likely to act, not those whose behaviour can be influenced by an intervention. Uplift modelling addresses this limitation by estimating the causal effect of a marketing intervention on individual customers, enabling firms to target those whose behaviour is expected to change as a result of treatment rather than those who would act regardless. This approach is especially relevant when marketing budgets are limited and effective resource allocation is essential.

This Master's thesis will develop and evaluate causal uplift models for targeted marketing campaigns, with applications in customer retention and promotion optimisation. Using randomised experimental datasets from domains such as telecommunications churn retention and email promotion campaigns, the project will implement and empirically compare state-of-the-art approaches including meta-learners (T-learner, S-learner, X-learner, DR-learner), tree-based uplift methods, and recent deep learning–based uplift models that explicitly model treatment effects via neural architectures.