Predictive Modeling in Procurement: A Framework for Using Spend Analytics and Forecasting to Optimize Inventory Control

@article{1703082,
      author = {Osazee Onaghinor, Ogechi Thelma Uzozie, Oluwafunmilayo Janet Esan, Emmanuel Augustine Etukudoh, Julius Olatunde Omisola},
      title = {Predictive Modeling in Procurement: A Framework for Using Spend Analytics and Forecasting to Optimize Inventory Control},
      journal = {Iconic Research And Engineering Journals},
      year = {2021},
      volume = {5},
      number = {6},
      pages = {312-322},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1703082.pdf},
      abstract = {Predictive modeling in procurement has become a critical tool for optimizing inventory control, improving demand forecasting, and enhancing supply chain efficiency. This study explores a comprehensive framework for leveraging spend analytics and forecasting techniques to drive data-driven procurement decisions. The research highlights key predictive modeling techniques, including machine learning and artificial intelligence, and their role in optimizing procurement strategies. By integrating historical spend analytics with predictive demand forecasting, organizations can enhance purchasing accuracy, minimize stock shortages, and reduce excess inventory costs. Furthermore, this study examines the challenges associated with predictive procurement models, such as data quality limitations, supplier performance variability, and algorithmic biases. The research also provides a data-driven approach to spend analytics, integrating internal and external data sources to improve procurement accuracy. Practical recommendations for implementing predictive procurement frameworks emphasize the importance of robust data infrastructure, phased deployment strategies, and cross-functional collaboration. The study concludes with strategic insights on measuring procurement performance, mitigating risks, and optimizing decision-making in inventory control. Future research directions include advancements in AI-driven procurement automation, blockchain integration, and ethical considerations in predictive analytics. This research contributes to the evolving field of procurement optimization, providing organizations with actionable strategies to enhance supply chain resilience and cost efficiency.},
      keywords = {Predictive Procurement, Spend Analytics, Demand Forecasting, Inventory Optimization, Machine Learning in Procurement, Supply Chain Efficiency},
      month = {December},
  }