請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98743完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 魏志平 | zh_TW |
| dc.contributor.advisor | Chih-Ping Wei | en |
| dc.contributor.author | 鐘閔祺 | zh_TW |
| dc.contributor.author | Min-Chi Chung | en |
| dc.date.accessioned | 2025-08-18T16:18:58Z | - |
| dc.date.available | 2025-08-19 | - |
| dc.date.copyright | 2025-08-18 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-06 | - |
| dc.identifier.citation | Carr, S. C., Inkson, K., & Thorn, K. (2005). From Global Careers to Talent Flow: Reinterpreting ‘Brain Drain’. Journal of World Business, 40(4), 386-398.
Caruana, R. (1997). Multitask Learning. Machine Learning, 28(1), 41-75. Cho, K., Van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014). On the Properties of Neural Machine Translation: Encoder-decoder Approaches. arXiv preprint arXiv:1409.1259. Groysberg, B., & Abrahams, R. (2006). Lift Outs: How to Acquire a High-functioning Team. Harvard Business Review, 84(12), 133-140. Gurman, M. (2021). Apple Aims to Prevent Defections to Meta With Rare $180,000 Bonuses for Top Talent. Bloomberg News. https://www.bloomberg.com/news/articles/2021-12-28/apple-pays-unusual-180-000-bonuses-to-retain-engineering-talent Hu, T. S., & Chen, K. C. (2014). Creative Talent Drive Transformation of Professionals’ Constitution in the Modern City: A Case Study of Fashion Talent Flow in Taipei. European Planning Studies, 22(5), 1081-1105. Jackson, D. J., Carr, S. C., Edwards, M., Thorn, K., Allfree, N., Hooks, J., & Inkson, K. (2005). Exploring the Dynamics of New Zealand's Talent Flow. New Zealand Journal of Psychology, 34(2). Lo, Y. L. (2024). CAR-TFP: Company-aware RNN-based Modeling for Talent Flow Prediction. Unpublished Master’s Thesis. Department of Information Management, National Taiwan University, Taipei, Taiwan, ROC. Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., & Chi, E. H. (2018). Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-experts. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013). Rectifier Nonlinearities Improve Neural Network Acoustic Models. Proceedings of ICML. Mao, G., Hu, B., & Song, H. (2009). Exploring Talent Flow in Wuhan Automotive Industry Cluster at China. International Journal of Production Economics, 122(1), 395-402. McKinsey & Company. (2018). Winning with Your Talent-management Strategy. https://www.mckinsey.com/capabilities/people-and-organizational- performance/our-insights/winning-with-your-talent-management-strategy McKinsey & Company. (2019). Giants Can Dance: Agile Organizations in Asset-heavy Industries. https://www.mckinsey.com/industries/oil-and-gas/our-insights/giants-can-dance-agile-organizations-in-asset-heavy-industries#/ McKinsey & Company. (2021). ‘Great Attrition’ or ‘Great Attraction’? The Choice is Yours. https://www.mckinsey.com/capabilities/people-and-organizational- performance/our-insights/great-attrition-or-great-attraction-the-choice-is-yours Oentaryo, R. J., Lim, E.-P., Ashok, X. J. S., Prasetyo, P. K., Ong, K. H., & Lau, Z. Q. (2018). Talent Flow Analytics in Online Professional Network. Data Science and Engineering, 3, 199-220. Project Management Institute. (2013). The Competitive Advantage of Effective Talent Management. Pulse of the Profession. Qin, C., Zhang, L., Cheng, Y., Zha, R., Shen, D., Zhang, Q., Chen, X., Sun, Y., Zhu, C., & Zhu, H. (2025). A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics. Proceedings of the IEEE. State, B., Rodriguez, M., Helbing, D., & Zagheni, E. (2014). Migration of Professionals to the US: Evidence from LinkedIn Data. Proceedings of Social Informatics: 6th International Conference, SocInfo 2014, Barcelona, Spain, November 11-13, 2014. Tarique, I., & Schuler, R. S. (2010). Global Talent Management: Literature Review, Integrative Framework, and Suggestions for Further Research. Journal of World Business, 45(2), 122-133. The Economist. (2024). Retention is All You Need. The Economist. https://www.economist.com/business/2024/06/08/the-war-for-ai-talent-is-heating-up Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA. Wang, P. L. (2023). What's Next After Quitting? Predicting the Next Job Using Time-series Embeddings. Unpublished Master’s Thesis. Department of Information Management, National Taiwan University, Taipei, Taiwan, ROC. Xu, H., Yu, Z., Yang, J., Xiong, H., & Zhu, H. (2018). Dynamic Talent Flow Analysis with Deep Sequence Prediction Modeling. IEEE Transactions on Knowledge and Data Engineering, 31(10), 1926-1939. Zhang, L., Zhu, H., Xu, T., Zhu, C., Qin, C., Xiong, H., & Chen, E. (2019). Large-scale Talent Flow Forecast with Dynamic Latent Factor Model? Proceedings of the World Wide Web Conference. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98743 | - |
| dc.description.abstract | 人才流動預測對企業制定有效的人才管理策略至關重要。在高度流動的全球勞動力環境中，企業必須分析人才市場動態，並制定相應策略以維持競爭力。透過人才流動預測，組織可以制定資料驅動的人才管理策略。現有研究已採用深度學習方法和線上專業網絡資料來解決人才流動預測問題。然而，這些研究專注在單向人才流動，因此未能捕捉人才流動的相互依賴性。此外，現有研究針對公司概況(company profile)的設計方式很難揭示組織特徵與人才流動之間的關係。
本研究旨在利用LinkedIn資料，開發深度學習模型進行人才流動預測。我們設計了雙向人才流動預測模型，此模型基於多任務成對架構以學習雙向的人才流動模式，並同時預測多方向的人才流動。此外，我們從人才流動紀錄中擷取具有時間性的公司特徵。我們的模型在預測人才流動量和辨識主要競爭公司方面皆展現出更優異的表現。 | zh_TW |
| dc.description.abstract | Talent flow prediction is critical for organizations in formulating effective talent management strategies. In today’s highly mobile global workforce, companies must analyze talent market dynamics and develop appropriate strategies to maintain their competitiveness. By leveraging talent flow prediction, organizations can develop data-driven strategies for talent management. Existing studies have applied deep learning methods and OPN data to address the talent flow prediction problem. However, these studies focus on uni-directional talent flow, which fails to capture the interdependent nature of talent flows. Moreover, the design of the company profile makes it difficult to reveal the relationship between organizational characteristics and talent flow.
This study aims to develop a deep learning model leveraging LinkedIn data for talent flow prediction. We design a bi-directional talent flow prediction model, based on multitask pair-wise architecture to learn the bi-directional flow patterns and predict talent flow of multiple directions simultaneously. In addition, we extract temporal company profile features from talent flow records. Our model achieves superior performance in predicting talent flow amount and identifying key competitor companies. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-18T16:18:58Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-18T16:18:58Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iii Table of Contents iv List of Figures vii List of Tables viii Chapter 1 Introduction 1 1.1 Background 1 1.2 Research Motivation and Objectives 5 Chapter 2 Literature Review 8 2.1 Talent Flow Prediction 8 2.1.1 Xu et al. (2018) 8 2.1.2 Lo (2024) 10 2.2 Research Gaps 12 Chapter 3 Methodology 16 3.1 Problem Formulation 16 3.2 Model Architecture 16 3.3 Transition Features and Transition Encoder 17 3.3.1 Transition Features 17 3.3.2 Transition Encoder 19 3.4 Profile Features and Profile Encoder 20 3.4.1 Profile Features 20 3.4.2 Profile Encoder 22 3.5 Profile Similarity Layer 23 3.6 Multitask Learning Layer 24 3.6.1 Multi-gate Mixture-of-Experts (MMoE) 24 3.7 Loss Weighting Strategy 26 Chapter 4 Data 27 4.1 Data Preprocessing 27 4.1.1 Data Collection and Cleaning 27 4.1.2 Company Filtering 28 4.1.3 Position Grouping 28 4.1.4 Talent Flow Extraction 30 4.1.5 Talent Flow Network Formation 31 4.2 Dataset Statistics 32 Chapter 5 Experiments 36 5.1 Dataset Arrangement and Splitting 36 5.2 Evaluation Metrics 37 5.3 Hyperparameter Settings 38 5.4 Benchmarks 39 5.5 Evaluation Results 43 5.6 Additional Evaluation Experiments 46 5.6.1 Evaluation of Multitask Learning Architectures 46 5.6.2 Evaluation of Time Series Models 48 5.6.3 Ablation Test of Feature Sets 49 5.6.4 Ablation Test of Transition Features 49 5.6.5 Effect of Loss Weighting Strategy 51 5.6.6 Effect of Number of Experts 51 Chapter 6 Conclusion 53 6.1 Conclusion 53 6.2 Future Works 54 References 56 | - |
| dc.language.iso | en | - |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 人才流動預測 | zh_TW |
| dc.subject | 序列建模 | zh_TW |
| dc.subject | 多任務學習 | zh_TW |
| dc.subject | 人才管理 | zh_TW |
| dc.subject | Deep Learning | en |
| dc.subject | Sequential Modeling | en |
| dc.subject | Multitask Learning | en |
| dc.subject | Talent Flow Prediction | en |
| dc.subject | Talent Management | en |
| dc.title | 動態公司感知的多任務學習方法於人才流動預測 | zh_TW |
| dc.title | Dynamic Company-Aware Multitask Learning for Talent Flow Prediction | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 向倩儀;楊錦生 | zh_TW |
| dc.contributor.oralexamcommittee | Chien-Yi Hsiang;Chin-Sheng Yang | en |
| dc.subject.keyword | 人才管理,人才流動預測,深度學習,多任務學習,序列建模, | zh_TW |
| dc.subject.keyword | Talent Management,Talent Flow Prediction,Deep Learning,Multitask Learning,Sequential Modeling, | en |
| dc.relation.page | 59 | - |
| dc.identifier.doi | 10.6342/NTU202503983 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-08-12 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2025-08-19 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 2.28 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。