An explainable hybrid deep learning framework for multi-source student employment prediction
Huanhuan Zheng, Jiayang Wu, Yingjiao Zhang · 2026
Read An explainable hybrid deep learning framework for multi-source student employment prediction by Huanhuan Zheng, Jiayang Wu, Yingjiao Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13572543.txt.
Description
Huanhuan Zheng, with two colleagues, presents a 2026 framework that forecasts what students do after a vocational college and shows its reasons. Outcomes split four ways: more study at home, a job, no job, or study abroad. Colleges want early, fair warnings, yet student data come from many sources and shift over time.
The model joins grades over time with background, finance, and activity records. A feature pruning step trims the input set first. A memory network with attention reads the grade path, while a tuned boosting model handles feature interplay. A tool called SHAP then shows how much each factor pushed a given call. On a real college data set, the model beat rival methods on accuracy and several other scores. The authors stress clear reasons, not just calls.
Catalog record
| CREATOR | Huanhuan Zheng, Jiayang Wu, Yingjiao Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64822 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |