PREF-VG: Topology-Conditioned Residual Adaptation for Probabilistic Multi-Horizon Student Engagement Forecasting
- 1School of Information Engineering, Guilin University, Guilin 541006, China
- 2College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China
- 3Department of Computer and Electrical Engineering, Mid Sweden University, 85170 Sundsvall, Sweden
Abstract
Forecasting student engagement can inform timely support in online education. However, the incremental predictive value of evolving behavioural topology beyond numerical temporal representations remains unclear. Here, behavioural engagement is operationalised through recorded activity in the virtual learning environment (VLE). We propose Prefix-based Residual Engagement Forecasting with Visibility Graphs (PREF-VG) for probabilistic multi-horizon forecasting. Within each observed window, natural visibility graphs yield ordered insertion-time descriptors of connection spans and local connectivity. A recurrent encoder summarises this sequence, and a gated residual adapter refines selected logit and log-mean parameters of a pretrained causal temporal convolutional network forecaster (Raw-TCN). The model estimates a hurdle negative-binomial click-count distribution and a binomial active-day marginal across four consecutive weeks from 56-day histories. Experiments on the Open University Learning Analytics Dataset used chronologically held-out course presentations and student-disjoint partitions. In the primary evaluation, under shared validation-based post-processing, results averaged across four horizons and five seeds showed that PREF-VG reduced click-count and active-day mean absolute errors by 3.24% and 4.19% relative to Raw-TCN, while increasing the area under the precision–recall curve for future inactivity from 0.7518 to 0.7686. On the primary test set, PREF-VG improved all five metrics over a parameter-matched raw-sequence adapter. In the alternative evaluation, gains over this control were supported for activity probabilities, inactivity ranking and active-day forecasts, with less certain click-count improvements. These comparisons support the incremental predictive value of insertion-time topology within the evaluated residual adaptation framework.
Related
- Two moments suffice for Bessel approximation: conditioned differences, contingency tables, and probabilistic divide-and-conquer
- SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs
- Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure
- The Markov Accessibility Topology and its Probabilistic Structure
- Combining Weather Forecast Aggregation and State-Space Models for Adaptive Probabilistic Electricity Load Forecasting
BibTeX
@article{xu2026prefvg,
title = {{PREF-VG: Topology-Conditioned Residual Adaptation for Probabilistic Multi-Horizon Student Engagement Forecasting}},
author = {Jinfeng Xu and Yancun Jiang and Qianxin Xie and Yuxuan Zhang},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14203735},
url = {https://www.mdpi.com/2227-7390/14/20/3735},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - PREF-VG: Topology-Conditioned Residual Adaptation for Probabilistic Multi-Horizon Student Engagement Forecasting
AU - Jinfeng Xu
AU - Yancun Jiang
AU - Qianxin Xie
AU - Yuxuan Zhang
PY - 2026
DA - 2026/10/14
JO - Mathematics
DO - 10.3390/math14203735
UR - https://www.mdpi.com/2227-7390/14/20/3735
AB - Forecasting student engagement can inform timely support in online education. However, the incremental predictive value of evolving behavioural topology beyond numerical temporal representations remains unclear. Here, behavioural engagement is operationalised through recorded activity in the virtual learning environment (VLE). We propose Prefix-based Residual Engagement Forecasting with Visibility Graphs (PREF-VG) for probabilistic multi-horizon forecasting. Within each observed window, natural visibility graphs yield ordered insertion-time descriptors of connection spans and local connectivity. A recurrent encoder summarises this sequence, and a gated residual adapter refines selected logit and log-mean parameters of a pretrained causal temporal convolutional network forecaster (Raw-TCN). The model estimates a hurdle negative-binomial click-count distribution and a binomial active-day marginal across four consecutive weeks from 56-day histories. Experiments on the Open University Learning Analytics Dataset used chronologically held-out course presentations and student-disjoint partitions. In the primary evaluation, under shared validation-based post-processing, results averaged across four horizons and five seeds showed that PREF-VG reduced click-count and active-day mean absolute errors by 3.24% and 4.19% relative to Raw-TCN, while increasing the area under the precision–recall curve for future inactivity from 0.7518 to 0.7686. On the primary test set, PREF-VG improved all five metrics over a parameter-matched raw-sequence adapter. In the alternative evaluation, gains over this control were supported for activity probabilities, inactivity ranking and active-day forecasts, with less certain click-count improvements. These comparisons support the incremental predictive value of insertion-time topology within the evaluated residual adaptation framework.
SN - 2227-7390
ER -