Advanced Procurement Analytics: Building a Model for Improved Decision-Making and Cost Efficiency within Global Supply Chains

ABISOLUWA ABRAHAM ODUTOLA
Independent Researcher
DOI – http://doi.org/10.37502/IJSMR.2022.5623

Abstract

This research paper investigates the application of advanced procurement analytics to enhance decision-making and cost efficiency in global supply chains. Utilizing Support Vector Machines (SVM) for predictive modeling and the Cox Proportional Hazards Model for risk assessment, the study develops a comprehensive model to optimize procurement processes. Integrating these advanced analytics techniques provides a data-driven approach to forecasting procurement needs, managing supplier risks, and improving overall cost efficiency.

The research incorporates a detailed survey conducted via SurveyMonkey to gather insights on procurement practices and supplier performance, which were analyzed using Alteryx for data visualization and integration. The findings demonstrate that the SVM model achieved an 85% accuracy rate in predicting procurement needs. At the same time, the Cox Proportional Hazards Model successfully identified critical risk factors with a concordance index of 0.78. Applying these models led to a 15% reduction in procurement costs and a 20% increase in inventory turnover rates.

The study highlights the practical implications of advanced analytics in procurement, emphasizing the potential for improved decision-making, enhanced cost efficiency, and strengthened risk management. The results underscore the importance of leveraging data-driven insights to address procurement challenges and optimize supply chain performance. Recommendations for future research include expanding data sources, exploring additional advanced analytics techniques, and conducting longitudinal studies to assess the long-term impact of these approaches.

Keywords: Advanced Procurement Analytics, Predictive Modeling, Support Vector Machine (SVM), Cox Proportional Hazards Model, Cost Efficiency, Risk Management, Global Supply Chains.

References

  1. Anderson, M., & Lee, H. (2017). “Procurement Analytics: Leveraging Big Data for Decision Making.” Journal of Supply Chain Management, 53(2), 34-47.
  2. (n.d). Alteryx Analytics Platform. Retrieved from https://www.alteryx.com
  3. Chopra, S., & Sodhi, M. (2014). “Managing Risk to Avoid Supply Chain Disruptions.” International Journal of Production Economics, 147, 50-59.
  4. Cox, D. (1972). “Regression Models and Life-Tables.” Journal of the Royal Statistical Society, 34(2), 187-220.
  5. Garcia, M., & Thomas, J. (2017). “Leveraging Machine Learning for Procurement Optimization.” Journal of Artificial Intelligence Research, 58, 123-137.
  6. Huang, Z., & Wang, J. (2019). “Forecasting Supplier Performance with SVM.” Computers & Industrial Engineering, 132, 283-291.
  7. Kleinbaum, D., & Klein, M. (2012). Survival Analysis: A Self-Learning Text. New York: Springer.
  8. Kumar, S., & Pal, R. (2018). “Predictive Analytics in Inventory Management.” International Journal of Production Economics, 196, 48-61.
  9. Nguyen, T., & Green, R. (2016). “Applications of Predictive Modeling in Procurement.” International Journal of Operations & Production Management, 36(9), 1180-1195.
  10. Smith, J., & Johnson, L. (2019). “The Evolution of Procurement Analytics.” International Journal of Procurement Management, 12(4), 256-272.
  11. Tang, C., & Tomlin, B. (2008). “The Power of Flexibility for Mitigating Supply Chain Risks.” International Journal of Production Economics, 116(1), 12-27.
  12. Williams, K., & Robinson, P. (2018). “Components of Procurement Analytics.” Journal of Business Analytics, 6(3), 120-135.
  13. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 1, pp. 1-33, Jan. 2020, doi: 10.1109/TPAMI.2019.2953823.