Stabilising Learner Trajectories: A Doubly Robust Evaluation of AI-Guided Student Support using Activity Theory

TL;DR

This study uses advanced causal inference methods to evaluate an AI-supported student intervention, finding it stabilizes at-risk students' academic trajectories and reduces failure rates, with implications for institutional policy.

Contribution

It introduces a novel evaluation methodology combining dynamic AI scores with propensity score matching and applies Activity Theory to interpret the socio-technical effects.

Findings

Intervention significantly reduced course failure rates

Supported students achieved higher cumulative grades

Effects on speed of qualification were positive but not statistically significant

Abstract

While predictive models are increasingly common in higher education, causal evidence regarding the interventions they trigger remains rare. This study evaluates an AI-guided student support system at a large university using doubly robust propensity score matching. We advance the methodology for learning analytics evaluation by leveraging time-aligned, dynamic AI probability of success scores to match 1,859 treated students to controls, thereby mitigating the selection and immortal time biases often overlooked in observational studies. Results indicate that the intervention effectively stabilised precarious trajectories, and compared to the control group, supported students significantly reduced their course failure rates and achieved higher cumulative grades. However, effects on the speed of qualification completion were positive but statistically constrained. We interpreted these findings through Activity Theory, framing the intervention as a socio-technical brake that interrupts and slows the accumulation of academic failure among at-risk students. The student support-AI configuration successfully resolved the primary contradiction of immediate academic risk, but secondary contradictions within institutional structures limited the acceleration of degree completion. We conclude that while AI-enabled support effectively arrests decline, translating this stability into faster progression requires aligning intervention strategies with broader institutional governance.