Quantum-Enhanced Learning Analytics for Adaptive Early Intervention in Higher Education

Overview

This project proposes a novel quantum-enhanced learning analytics framework for higher education, focusing on early identification of at-risk students and optimisation of intervention strategies using hybrid quantum-classical approaches. While current learning analytics systems rely on classical statistical and machine learning techniques, they often struggle to capture the complex, uncertain, and multi-dimensional nature of student learning behaviours.

This research introduces quantum-inspired representations and optimisation techniques to model student engagement, performance trajectories, and behavioural uncertainty more effectively, enabling more accurate predictions and improved decision-making in educational contexts.

Research Objectives

• Develop quantum-inspired models to represent student learning states using probabilistic and high-dimensional feature spaces.
• Design predictive models for early identification of at-risk students using both classical and quantum-inspired approaches.
• Apply hybrid optimisation techniques (e.g., quantum-inspired or QAOA-based methods) to determine optimal intervention strategies under resource constraints.
• Compare the performance, scalability, and interpretability of quantum-inspired models against classical machine learning methods.
• Develop a prototype system integrated with learning management system (LMS) data (e.g., Moodle) to demonstrate real-world applicability.

Methodology

The project will utilise large-scale educational datasets derived from learning management systems such as Moodle, including student engagement metrics (e.g., login frequency, assessment attempts, submission patterns, and interaction logs). The methodology consists of three key stages:

1. Classical Baseline Modelling: Implementation of standard machine learning models (e.g., Random Forest, Gradient Boosting, Neural Networks) to establish performance benchmarks.
2. Quantum-Inspired Modelling: Development of probabilistic and state-based representations inspired by quantum systems to model uncertainty and complex behavioural patterns.
3. Hybrid Optimisation Framework: Application of quantum-inspired optimisation techniques, including variational and combinatorial approaches, to improve intervention strategies and resource allocation.

Where feasible, simulations will be conducted using quantum development frameworks such as Qiskit to evaluate potential advantages and limitations of near-term quantum systems.

Expected Contributions

• A novel quantum-enhanced framework for learning analytics in higher education.
• Improved methods for early detection of at-risk students.
• Optimisation models for personalised and resource-efficient educational interventions.
• Empirical benchmarking of quantum-inspired approaches against classical methods.
• A scalable prototype system demonstrating practical applicability in real educational settings.