Forecasting Internal Labor Supply at Baganuur JSC, A Strategic Energy Hub of Mongolia: A Markov Chain Analysis

Workforce planning and forecasting are critical for enhancing organizational performance, particularly in capital-intensive industries. This study analyzes and forecasts the internal labor supply of Baganuur JSC, a state-owned coal mining company in Mongolia, using a Markov chain model. The analysis draws on historical human resource data spanning 2005–2014, from which transition probabilities across workforce segments—including age, education level, gender, and tenure—are estimated. The findings reveal a pronounced aging trend, with a growing proportion of employees approaching retirement age, signaling a potential risk of labor shortages and loss of experienced personnel. Scenario analysis further demonstrates that variations in hiring and attrition rates significantly influence long-term workforce stability. Based on the quantitative forecasts, the study derives actionable strategic insights: by 2035, approximately 40% of the workforce is projected to be aged 50 or above, necessitating an estimated 60–80 new hires annually to sustain operational capacity. Three scenario-based HR strategy frameworks—baseline, high-attrition, and accelerated recruitment—are presented to support succession planning and human capital sustainability. The findings contribute to the limited body of quantitative workforce forecasting research in developing economies and provide data-driven decision-making tools for HR managers in Mongolia's mining sector.

human resource management; internal labor supply; workforce planning; Markov chain model; labor forecasting; mining industry; Mongolia

1. Bartholomew, D. J., Forbes, A. F., & McLean, S. I. (1991). Statistical techniques for manpower planning (2nd ed.). Wiley. [Google Scholar] [Crossref]

2. De Feyter, T. (2006). Modeling heterogeneity in manpower planning: Dividing the personnel system into more homogeneous subgroups. Applied Stochastic Models in Business and Industry, 22(4), 321–334. [Google Scholar] [Crossref]

3. Goh, Y. M., & Law, K. S. (2019). Hybrid Markov chain and machine learning models for workforce analytics. Human Resource Management Review, 29(3), 100–115. [Google Scholar] [Crossref]

4. Sambalkhundav, D. (2000). Human resource management. Ulaanbaatar. [Google Scholar] [Crossref]

5. Taylor, S. (2005). People resourcing (3rd ed.). Chartered Institute of Personnel and Development. [Google Scholar] [Crossref]

6. Tsetsegmaa, Ts. (2009). Human resource management: Theory, practice, examples. Ulaanbaatar. (487 pp.) [Google Scholar] [Crossref]

7. Tseveenjav, J., Naranbat, M., Otgonsuren, S., & Undarmaa, D. (2012). Human resource research in drilling profession: Problems facing the drilling department of Mongolia and solutions. Ulaanbaatar, 1(14), 5–18. [Google Scholar] [Crossref]

8. Tseveenjav, J., Otgonsuren, S., Odsaikhan, N., & Olziisaikhan, O. (2013). Human resources in the petroleum sector. Petroleum-2013, Ulaanbaatar, 1(19), 258–261. [Google Scholar] [Crossref]

9. Vassiliou, P.-C. G. (1992). The evolution of the theory of non-homogeneous Markov systems. Applied Stochastic Models and Data Analysis, 8(4), 397–424. [Google Scholar] [Crossref]

10. The transition dynamics visualized in the matrix heatmap (see Figure 1) confirm the high stability of the core workforce, while highlighting the deterministic nature of age-based transitions. [Google Scholar] [Crossref]

• Smart Iot Device for Weather And Health
• Merlarchive: A Web-Based Academic Hub for UDM With AI-Powered Natural Language Processing
• Enhanced Social Network Security System: Integrating Biometric Authentication for Improved User Verification and Privacy Protection
• Smart Budget Allocation in Public Policy: A Data-Driven Approach for Equitable Resource Distribution
• Decision Support System for Faculty Selection, Promotion, and Reclassification Using Predictive Analytics