Academic Benchmark Dashboard

Li, H., Ding, W., & Liu, Z. (2020). Identifying At-Risk K-12 Students in Multimodal Online Environments: A Machine Learning Approach. arXiv:2003.09670.

Combining multiple modalities of online-activity data flags at-risk students earlier and more reliably than any single source — the core fusion idea behind this dashboard.

Chung, J. Y., & Lee, S. (2019). Dropout early warning systems for high school students using machine learning. Children and Youth Services Review.

Administrative student data can drive accurate, actionable early-warning predictions at scale — risk scores here surface a ranked watch list for leadership.

Samuelsen, J., Chen, W., & Wasson, B. (2019). Integrating multiple data sources for learning analytics. Research and Practice in Technology Enhanced Learning, 14(11).

Most learning-analytics studies integrate only two sources, which biases insight — this module fuses four: online learning, parent involvement, conduct, and score trends.

Guo, T., Zhao, W., Alrashoud, M., Tolba, A., Firmin, S., & Xia, F. (2022). Multimodal educational data fusion for students' mental health detection. IEEE Access, 10.

Fusing heterogeneous educational data extends risk detection beyond academics into wellbeing — engagement signals carry weight alongside performance.

Modeling Behavior Change for Multi-model At-Risk Students Early Prediction (extended version, 2025). arXiv:2503.05734.

Modeling how behavior changes over time, not just a snapshot — the Trend signal compares each student's recent online scores against their early-year baseline.