Energy ELEMENTS

MULTI-MODAL ENSEMBLE LEARNING ARCHITECTURE FOR LABOR MARKET’S DIGITAL TRANSFORMATION

Assylbek Gizatov

Senior Research Scientist, Research Institute of Mathematics and Applied Technologies, Atyrau University named after Kh. Dosmukhamedov, Kazakhstan
E-mail: a.gizatov@asu.edu.kz | ORCID: 0009-0009-2557-0767

Nurtas Zhaksybayev

Master’s student in Applied Data Analytics, School of AI and Data Science, Astana IT University, Kazakhstan
E-mail: 255235@astanait.edu.kz | ORCID: 0009-0008-1031-3795

Alibi Jangeldin

M.Sc in Statistics, Senior-Lecturer, Department of Computing and Data Science, Astana IT University, Kazakhstan
ORCID: 0009-0000-0990-4362

Abstract

The rapid growth of educational grants in Kazakhstan has led to wage stagnation and oversaturation in key sectors. This study presents a meta-model combining CatBoost, Explainable Boosting Machine (EBM), and Bayesian-optimized LSTM neural networks to forecast wages, analyze labor market factors, and predict sector demand trends. Findings highlight critical oversupply risks, providing policymakers actionable insights for aligning education with economic needs, fostering sustainable development.

Keywords: Kazakhstan, labor market, wage stagnation, educational grants, machine learning, CatBoost, Explainable Boosting Machine (EBM), Long Short-Term Memory (LSTM), Bayesian optimization, demand forecasting, economic sustainability.

References:

  1. Alshammari, R., Alshammari, T., Singh, S., & Rawat, D. B. (2023). A comprehensive review on ensemble deep learning: Opportunities and challenges. Intelligent Systems with Applications, 18, 200228.
  2. Box, G. E. P., & Cox, D. R. (1964). An analysis of transformations. Journal of the Royal Statistical Society: Series B (Methodological), 26(2), 211–243.
  3. Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015). Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1721–1730.
  4. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). Catboost: Gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.
  5. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
  6. Kaabar, S. (2024). Use catboost to predict your time series. Medium. Retrieved May 16, 2025.
  7. Karimov, A., Khasanov, T., & Ibragimov, R. (2025). Generalized meta framework for forecasting. ResearchGate.
  8. Liang, J., Jiang, L., Moreno, A., Zou, J., Fei-Fei, L., Niebles, J. C., & Sun, C. (2023). Advances in deep ensemble learning: Trends and perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10633–10651.
  9. Liu, J., Wang, H., Zhang, Y., & Chen, X. (2024). Two-stage meta-ensembling machine learning model for enhanced predictive analytics. Journal of Hydrology, 628, 130136..
  10. Microsoft Research. (2023). Train explainable boosting machines — classification. Microsoft Learn. Retrieved May 16,*2025.
  11. Nori, H., Jenkins, S., Koch, P., & Caruana, R. (2019). InterpretML: A unified framework for machine learning interpretability. arXiv preprint arXiv:1909.09223.
  12. Patel, R., Kumar, A., & Singh, V. (2024). LSTM adaptive hyperparameter tuning for financial time series forecasting. Journal of Theoretical and Applied Information Technology, 102(24).
  13. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). Catboost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31, 6638–6648.
  14. Ren, Y., Suganthan, P. N., & Srikanth, N. (2021). The ensemble approach to forecasting: A review and synthesis. Transportation Research Part C: Emerging Technologies, 132, 103357.
  15. Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems, 25, 2951–2959.
  16. Wu, J., Chen, X. -Y., Zhang, H., Xiong, L. -D., Lei, H., & Deng, S. -H. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26–40.
  17. Yeo, I. -K., & Johnson, R. A. (2000). A new family of power transformations to improve normality or symmetry. Biometrika, 87(4), 954–959.
  18. Zhang, W., Li, X., Chen, J., & Wang, Y. (2025). Developing an ensemble machine learning framework for enhanced predictive modeling. Nature Communications Earth & Environment, 6(1), 133.
Energy ELEMENTS, Issue 1, 2026_MULTI-MODAL ENSEMBLE LEARNING ARCHITECTURE FOR LABOR MARKET’S DIGITAL TRANSFORMATIONOpen