Back to search

CSUniversity San Bernardino

PREDICTING LATE DELIVERIES IN INTERNATIONAL HEALTHCARE LOGISTICS USING MACHINE LEARNING MODELS

Abstract

dc:description.abstract

The healthcare supply chain plays a pivotal role in ensuring the timely delivery of essential medical supplies, particularly during global crises such as the COVID-19 pandemic. However, this critical system is often plagued by inefficiencies and disruptions caused by factors such as inadequate infrastructure, natural disasters, geopolitical tensions, and variability in vendor performance. These challenges underscore the need for advanced methodologies to enhance supply chain resilience and operational efficiency. This culmination experience project explores the integration of machine learning models and external variables, such as the Logistics Performance Index (LPI), to optimize lead-time predictions and mitigate risks in global healthcare supply chains. The research questions are: (Q1) What are the influential factors in health care logistics on-time deliveries? (Q2) How can predictive analytics and machine learning models be used to identify the shipments with high chance of late deliveries in healthcare logistics? (Q3) What role does the integration of external variables like the country logistics capabilities play in improving the accuracy of prediction of healthcare logistics performance, and why is this critical? The findings reveal that machine learning models, including random forest regression and hybrid algorithms such as WKM_ID3, effectively identify critical factors influencing delays, such as transportation modes and vendor terms, significantly enhancing prediction accuracy and operational efficiency. Furthermore, the integration of the LPI provides a comprehensive framework for understanding how national logistics capabilities influence delivery timelines, thereby enabling proactive risk mitigation strategies. These findings highlight the transformative potential of data-driven approaches in healthcare logistics. The study concludes that leveraging predictive analytics allows healthcare supply chains to transition from reactive to proactive management, fostering enhanced resilience and efficiency. Incorporating external indicators like the LPI further strengthens predictive capabilities, offering actionable insights into addressing systemic vulnerabilities. Future research could investigate the long-term implications of machine learning-enabled logistics on cost-effectiveness, global healthcare accessibility, and sustainability. Additionally, examining the regulatory and geopolitical constraints impacting healthcare supply chains offers valuable avenues for further exploration.

Degree

thesis:*
Name thesis:degree_name
Master of Science in Information Systems and Technology
Level thesis:degree_level
Project
Discipline thesis:degree_discipline
Information and Decision Sciences

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Gali, Jeevan Sai
Contributors dc:contributor
  • Nima Molavi

Subjects

dc:subject × 6

Identifiers

dc:identifier.*
Repository record dc:identifier
https://scholarworks.lib.csusb.edu/etd/2182

Chain of custody

source
Harvested from
CSUniversity San Bernardino
Base URL
scholarworks.lib.csusb.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Gali, Jeevan Sai. PREDICTING LATE DELIVERIES IN INTERNATIONAL HEALTHCARE LOGISTICS USING MACHINE LEARNING MODELS. Project thesis, https://scholarworks.lib.csusb.edu/etd/2182