Research map / Probabilistic and scientific modeling / Molecules and proteins
Exploiting the Contagious Effect for Employee Turnover Prediction
Mingfei Teng, Hengshu Zhu, Chuanren Liu, Chen Zhu, Hui Xiong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add environmental-change sequence, profile and global attention to turnover-sequence-only RNN (CEHNN) (ablation) | Turnover sequence RNN · Turnover dataset | accuracy: 0.853±0.022 -> 0.864±0.018 | Improved |
| add turnover sequence + profile + attention to environmental-change-only RNN (ablation) | Environmental change RNN · Turnover dataset | AUC-ROC: 0.804±0.045 -> 0.914±0.02 | Improved |
| use sequence-aware CEHNN instead of Gradient Boosting on concatenated features | Gradient Boosting · Turnover dataset | AUC-ROC: 0.910±0.026 -> 0.914±0.02 | Improved |
| use CEHNN instead of Gradient Boosting when positive/negative ratio reduced (less data) | CEHNN · Turnover dataset, varied pos/neg ratio | AUC-ROC | Hurt |
| lengthen observation period | CEHNN vs Gradient Boosting and Random Forest · Turnover dataset, observation period 3 to 12 months | AUC-ROC | Mixed |
| use HMM instead of neural sequence models | turnover sequence models · Turnover dataset | AUC-ROC: 0.905±0.025 -> 0.55±0.088 | Hurt |
Closest papers by meaning
- Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking (NeurIPS 2024 · similarity 0.80)
- A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction (AAAI 2024 · similarity 0.79)
- A Mathematical Framework for AI-Human Integration in Work (ICML 2025 · similarity 0.78)
- How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies (ICML 2025 · similarity 0.78)
- PLD: A Choice-Theoretic List-Wise Knowledge Distillation (NeurIPS 2025 · similarity 0.76)
- Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations (ICML 2025 · similarity 0.76)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
