When Administrative Networks Fail: Curriculum Structure, Early Performance, and the Limits of Co-enrolment Social Synchrony for Dropout Prediction in Engineering Education

• URL: http://arxiv.org/abs/2511.17736v1
• Date: Fri, 21 Nov 2025 19:38:25 GMT
• Title: When Administrative Networks Fail: Curriculum Structure, Early Performance, and the Limits of Co-enrolment Social Synchrony for Dropout Prediction in Engineering Education
• Authors: H. R. Paz,
• Abstract summary: Social integration theories suggest students embedded in supportive peer networks are less likely to drop out.<n>In learning analytics, this has motivated the use of social network analysis (SNA) from institutional co-enrolment data to predict attrition.<n>This study tests whether such administrative network features add predictive value beyond a leakage-aware, curriculum-graph-informed model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Social integration theories suggest that students embedded in supportive peer networks are less likely to drop out. In learning analytics, this has motivated the use of social network analysis (SNA) from institutional co-enrolment data to predict attrition. This study tests whether such administrative network features add predictive value beyond a leakage-aware, curriculum-graph-informed model in a long-cycle Civil Engineering programme at a public university in Argentina. Using a three-semester observation window and a 16-fold leave-cohort-out design on 1,343 students across 15 cohorts, we compare four configurations: a baseline model (M0), baseline plus network features (M1), baseline plus curriculum-graph features (M2), and a full model (M3). After a leakage audit removed two post-outcome variables that had produced implausibly perfect performance, retrained models show that M0 and M2 achieve F1 = 0.9411 and ROC-AUC = 0.9776, while adding network features systematically degrades performance (M1 and M3: F1 = 0.9367; ROC-AUC = 0.9768). We conclude that in curriculum-constrained programmes, administrative co-enrolment SNA does not provide additional risk information beyond curriculum topology and early academic performance.

Related papers

• Explainable Deep Learning for Brain Tumor Classification: Comprehensive Benchmarking with Dual Interpretability and Lightweight Deployment [4.259927630334864]
  This study provides a full deep learning system for automated classification of brain tumors from MRI images.<n>Inception-ResNet V2 reached state-of-the-art performance, achieving a 99.53% accuracy on testing.<n>This end-to-end solution considers accuracy, interpretability, and deployability of trustworthy AI.
  arXiv  Detail & Related papers  (2025-11-20T17:21:40Z)
• The CAPIRE Curriculum Graph: Structural Feature Engineering for Curriculum-Constrained Student Modelling in Higher Education [0.0]
  This paper introduces the CAPIRE Curriculum Graph, a structural feature engineering layer embedded within the CAPIRE framework for student attrition prediction.<n>We derive nine structural features at the student-semester level that capture how students navigate the prerequisite network over time.<n>These features include backbone completion rate, bottleneck approval ratio, blocked credits due to incomplete prerequisites, and graph distance to graduation.
  arXiv  Detail & Related papers  (2025-11-19T15:33:00Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Teaching Language Models to Reason with Tools [73.21700643314917]
  We present emphHint-Engineering, a new data synthesis strategy that strategically injects diverse hints at optimal points within reasoning paths.<n>CoRT significantly enhances efficiency, reducing token usage by approximately 30% for the 32B model and 50% for the 1.5B model.
  arXiv  Detail & Related papers  (2025-10-23T08:41:44Z)
• Detect Anything via Next Point Prediction [51.55967987350882]
  Rex- Omni is a 3B-scale MLLM that achieves state-of-the-art object perception performance.<n>On benchmarks like COCO and LVIS, Rex- Omni attains performance comparable to or exceeding regression-based models.
  arXiv  Detail & Related papers  (2025-10-14T17:59:54Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence [61.46575527504109]
  LimiX-16M and LimiX-2M treat structured data as a joint distribution over variables and missingness.<n>We evaluate LimiX models across 11 large structured-data benchmarks with broad regimes of sample size, feature dimensionality, class number, categorical-to-numerical feature ratio, missingness, and sample-to-feature ratios.
  arXiv  Detail & Related papers  (2025-09-03T17:39:08Z)
• Privacy-Preserved Automated Scoring using Federated Learning for Educational Research [1.2556373621040728]
  We propose a federated learning (FL) framework for automated scoring of educational assessments.<n>We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline.<n>Results show that our model achieves the highest accuracy (94.5%) among FL approaches.
  arXiv  Detail & Related papers  (2025-03-12T19:06:25Z)
• Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training [68.94373533768501]
  We model knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training.<n>We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy.
  arXiv  Detail & Related papers  (2025-02-06T13:23:53Z)
• Network Gradient Descent Algorithm for Decentralized Federated Learning [0.2867517731896504]
  We study a fully decentralized federated learning algorithm, which is a novel descent gradient algorithm executed on a communication-based network. In the NGD method, only statistics (e.g., parameter estimates) need to be communicated, minimizing the risk of privacy. We find that both the learning rate and the network structure play significant roles in determining the NGD estimator's statistical efficiency.
  arXiv  Detail & Related papers  (2022-05-06T02:53:31Z)
• Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks [50.68446003616802]
  Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices. We develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning.
  arXiv  Detail & Related papers  (2022-02-07T05:11:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.