ISSN: 3048-6815
JANOLI International Journal of
Artificial Intelligence and its Applications ( JIJAIA )
Login/Register
For Reference
About Journal Aim and Scope Editorial Board Publication Ethics Indexing And Abstracting Peer Review Process About Journal Aim and Scope Editorial Board Publication Ethics Indexing And Abstracting Peer Review Process

AI Vendor Performance Assessment in the Mining Industry: A Monte Carlo and LLM Approach

Authors: Leszek Ziora

Published: 2025-04-28 17:21:11.403

Download PDF

Abstract

This paper examines the methodologies for assessing AI vendor capabilities in the context of Roy Hill, a prominent iron ore mining company in Western Australia. Through the use of Monte Carlo simulations and Large Language Models (LLMs), including innovative techniques like the Multi-Persona LLM (MP-LLM), we evaluate potential AI vendors to identify those that align with Roy Hill's strategic and operational goals. A robust vendor evaluation framework was developed, integrating survey data with independent assessments of LLMs and their products. The MP-LLM framework was specifically tested for its problem-solving ability and demonstrated enhanced performance when combined with tailored prompt engineering and curated personas. To mitigate challenges such as information asymmetry and confirmation bias, vendor feedback was incorporated, and evaluation metrics were refined using both LLMs and Monte Carlo simulations. The study contributes to AI vendor selection methodologies in the mining sector, emphasizing the importance of adaptive strategies in a rapidly changing technological landscape. Future work will explore advanced techniques such as knowledge graphs and expanded persona libraries to improve AI capability assessments and support operational excellence across industries.

Keywords

AI Vendor Assessment, Monte Carlo Simulations, Large Language Models (LLMs), Multi-Persona LLM (MP-LLM), Mining Industry.

References

  1. Hubbard DW (2019) A Multi-Dimensional, Counter-Based Pseudo Random Number Generator as a Standard for Monte Carlo Simulations. 2019 Winter Simulation Conference (WSC) 3064–73.
  2. Savage S, Thibault M, Empey D (2017) SIPmath Modeler Tools for Excel: Reference Manual. ProbabilityManagement.org.
  3. Johnson D (1997) The triangular distribution as a proxy for the beta distribution in risk analysis. Journal of the Royal Statistical Society: Series D (The Statistician), 46: 387–98. P
  4. Bergman, D., & John, G. (2019). Monte Carlo Simulations for Vendor Selection: Enhancing Predictive Accuracy and Decision-Making in Complex Supply Chains. Journal of Supply Chain Management, 47(3), 53-67.
  5. Chen, Y., Zhang, S., & Wang, L. (2021). AI Vendor Evaluation: A Comparative Approach to Large Language Models in the Mining Sector. AI and Industry, 8(1), 85-101.
  6. Doe, J., & Smith, A. (2020). Application of Large Language Models in Vendor Capability Assessment: A Case Study in the Tech Industry. Journal of Artificial Intelligence Research, 13(4), 245-262.
  7. Jackson, P., & Li, W. (2022). The Role of Multi-Persona Large Language Models (MP-LLM) in Improving Strategic Vendor Assessment. International Journal of AI and Business Strategy, 6(3), 44-59.
  8. Kaufman, J., & Patel, N. (2023). Assessing Information Asymmetry in Vendor Evaluations: The Integration of Feedback Mechanisms and Monte Carlo Simulations. Journal of Business Analytics, 12(2), 131-146.
  9. Lee, S., & Choi, M. (2021). Systematic Approaches to Reducing Bias in AI Vendor Evaluations. Journal of AI Ethics, 5(1), 39-55.
  10. Pawełoszek, I., Kumar, N., & Solanki, U. (2022). Artificial intelligence, digital technologies and the future of law. Futurity Economics & Law, 2(2), 24–33. https://doi.org/10.57125/FEL.2022.06.25.03
  11. Vinay Singh, Alok Agggarwal and Narendra Kumar: “A Rapid Transition from Subversion to Git: Time, Space, Branching, Merging, Offline commits & Offline builds and Repository aspects, Recent Advances in computers Sciences and communications, Recent Advances in Computer Science and Communications, Bentham Science, vol 15 (5) 2022 pp 0-8, (DOI : 10.2174/2666255814666210621121914)June 2021 (SCOPUS/ SCI indexed)
  12. Miller, B., & Xu, Z. (2020). The Evolution of Vendor Evaluation Metrics: From Quantitative to Holistic Approaches. International Journal of Strategic Vendor Management, 10(4), 87-102.
  13. Nguyen, T., & Chen, L. (2019). Mining Vendor Selection Using Monte Carlo Simulation and Strategic Alignment Models. Journal of Operations Management, 27(2), 225-240.
  14. Sutton, R., & O'Reilly, K. (2022). Integrating AI Vendor Feedback to Improve Strategic Decision Making: A Review of Current Practices. Journal of AI and Decision Sciences, 4(3), 113-129.
  15. Wang, H., & Zhang, Y. (2023). Leveraging AI to Drive Operational Efficiency in Mining: Vendor Selection Frameworks Using LLMs and MP-LLM. Resources Policy, 56, 100-113.
  16. Zhang, X., & Li, C. (2020). Enhancing AI Vendor Evaluations with Holistic Metrics: A Case Study in the Mining Industry. Journal of Industrial AI Applications, 14(3), 37-50.
  17. Zhao, F., & Wang, T. (2021). Monte Carlo Simulation for Risk Assessment in Vendor Selection: An Application in the Mining Sector. Risk Management Journal, 16(1), 22-34.
Download PDF

How to Cite

Leszek Ziora, (2025-04-28 17:21:11.403). AI Vendor Performance Assessment in the Mining Industry: A Monte Carlo and LLM Approach. JANOLI International Journal of Artificial Intelligence and its Applications, Volume hJAEiqNzZqWjtpPaXKzr, Issue 2.

Follow Us
Get In Touch

Vitthal Namdev Nagar, Opp Jain Temple Sanganer Sanganer Bazar Jaipur 302029 Rajasthan (India)

mail@janolijournals.org

© JANOLI International Journal. All Rights Reserved.