Cloud-Enabled Machine Learning: A Framework for Revolutionizing Pharmacy Inventory Management in Nairobi County

Main Article Content

Kelvin Chebet
Vincent Mbandu

Abstract

This study assesses the impact of cloud-based machine learning on pharmacy inventory management in Nairobi County, Kenya. Traditional pharmacy inventory management results in challenges such as stock-outs and overstocking, which affect financial performance and patient care. The study uses the EOQ and JIT theories to analyze how cloud computing through AWS PaaS and machine learning through the XGBoost algorithm can improve inventory management. A descriptive research design was used, and a target population was 100 pharmacies (65 public and 35 private) in Nairobi County. Structured questionnaires were administered to the pharmacy managers and staff to determine their current practices and perceptions of the proposed cloud-based machine learning framework. Quantitative data was analyzed through regression and correlation analyses. The findings indicated that AWS PaaS improved efficiency by 65%, scalability by 60%, and security by 65%, while XGBoost improved forecast accuracy by 65% and reduced stock outs by 65%. Regression analysis showed a strong predictive power with an R-value of 0.922, and a high p-value of 1.274; showing a statistical insignificance in explaining the variance in inventory management. Similarly, although XGBOOST is a statistically significant predictor (p-value of 0.017), AWS is a statistically insignificant predictor with a p-value of 1.283. Correlation analysis revealed strong positive relationship between the technologies and inventory management. The study concludes that the combination of cloud computing and machine learning can transform the management of pharmacy inventory, including problems that have remained persistent, such as stock-outs and overstocking. The major recommendations are that the proposed framework should be implemented in pharmacies by the management, management should ensure continuous staff training on the use of technologies, and that their performance should be monitored. This research offers an industry-specific, integrated framework to apply advanced technologies for improving efficiency, accuracy, and cost in the pharmaceutical supply chain.

Article Details

How to Cite
Chebet, K., & Mbandu, V. (2024). Cloud-Enabled Machine Learning: A Framework for Revolutionizing Pharmacy Inventory Management in Nairobi County. International Journal of Professional Practice, 12(6), 15–27. Retrieved from http://ijpp.kemu.ac.ke/index.php/ijpp/article/view/457
Section
Browse Articles in this Issue