Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

An explainable hybrid deep learning framework for multi-source student employment prediction.

Huanhuan Zheng¹, Jiayang Wu², Yingjiao Zhang³

¹Zhejiang Business College, Hangzhou, 310053, China.

Scientific Reports

|June 22, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Temporal microbial succession informs the reformulation of a defined four-member starter for fermented milk.

International journal of food microbiology·2026

Same author

Role of spectral CT in quantitative evaluation of pathologic response to neoadjuvant immunochemotherapy in esophageal squamous cell carcinoma: a pilot study.

Journal of translational medicine·2026

Same author

Liver CT-based composite biomarkers can identify MASH and steatosis grade in people with obesity prior to bariatric surgery: a retrospective study.

BMC gastroenterology·2026

Same author

The green spark of partial reform: Evidence from China's electricity market experiment.

PNAS nexus·2026

Same author

A novel hierarchical temporal refinement diffusion network for data augmentation of industrial soft sensors.

ISA transactions·2026

Same author

Deep Learning-Based Prediction of Trabecular Bone Mineral Density From Lumbar CT: A Superior Alternative to DEXA in Hyperostosis.

Global spine journal·2026

This study introduces an explainable deep learning model for predicting student employment outcomes using diverse data. The framework accurately forecasts career success, offering valuable insights for educational and career guidance.

Area of Science:

Educational Data Mining
Artificial Intelligence
Machine Learning

Background:

Predicting student employment outcomes is complex due to diverse student backgrounds and dynamic labor markets.
Existing methods often struggle to integrate heterogeneous data sources effectively.

Purpose of the Study:

To develop an explainable hybrid deep learning framework for multi-class student employment prediction.
To integrate multi-source heterogeneous data for enhanced prediction accuracy and interpretability.

Main Methods:

Recursive feature elimination for feature selection.
Bi-directional long short-term memory network with attention for temporal patterns.
XGBoost classifier optimized by tree-structured Parzen estimator for feature interactions.

Related Experiment Videos

SHAP values for model interpretability.

Main Results:

The proposed framework significantly outperformed baseline models across key metrics (accuracy, macro-F1, AUC, Cohen's kappa).
The model effectively leveraged both longitudinal academic data and static characteristics.
SHAP values provided clear explanations for feature contributions to predictions.

Conclusions:

The hybrid deep learning framework offers an accurate and interpretable solution for predicting student employment outcomes.
This approach can aid educational institutions and students in navigating career pathways.
The integration of diverse data sources and explainability enhances the practical utility of predictive models.