Instructions and Guide: Causal Insights for Learning Paths in Education

Causal machine learning is a field that focuses on using machine learning methods to tackle causality problems. Despite the recent progress in this field, there are still many unresolved challenges, including missing data, selection bias, unobserved confounders, etc., which are ubiquitous in the real world. Advances in any of the above areas can greatly reduce the gap between research and real-world impact. In this competition, we focus on two fundamental challenges of causal machine learning in the context of education using time-series data. The first is to identify the causal relationships between different constructs, where a construct is defined as the smallest element of learning. The second challenge is to predict the impact of learning one construct on the ability to answer questions on other constructs. Addressing these challenges will not only impact the causal ML community but also enable optimisation of students' knowledge acquisition, which can be deployed in a real edtech solution impacting millions of students. Participants will run these tasks in an idealised environment with synthetic data and a real-world scenario with evaluation data collected from a series of A/B tests. We expect participants to develop novel machine learning methodologies for causal discovery between different constructs and the impact estimation of learning one construct on other constructs, which should bring fundamental advances to causal ML.