This capstone project aims to use machine learning techniques to predict global supply chain outcomes for essential HIV medicines using procurement transaction data. The research addresses the lack of accurate and timely information about the global supply chain, which can lead to disruptions and delays. The project objectives are to collect and clean the data, develop a predictive model, evaluate the model's performance, and identify patterns and trends in the data. The research questions are to determine the effectiveness of machine learning techniques in predicting outcomes and identify critical factors that influence the supply chain. The study found that machine learning techniques could effectively predict outcomes, and factors such as destination mean, destination sum, destination count, origin mean, origin sum, origin count, origin fragility index, and year significantly correlate with delays in the supply chain. The recommended next steps include further analysis, real-time monitoring, and expansion to other regions.
The global supply chain for essential HIV medicines is a complex and dynamic system critical for ensuring the timely and efficient delivery of these life-saving drugs to patients in need. However, managing this supply chain can be challenging, as it involves multiple stakeholders, including manufacturers, distributors, and governments. It is subject to many external factors, such as economic conditions, political instability, and natural disasters. According to (Devex, 2018), only a small fraction of individuals living with HIV, 19.5 million out of the approximate 37 million, are receiving the essential medicines they require. The availability of these vital medicines is crucial. Studies show that the supply chain for major global programs is facing difficulties, as reported in (Devex, 2018), due to changes in the organizations managing the supply chain.
The specific problem that this research project aims to address is the lack of accurate and timely information about the global supply chain for essential HIV medicines. This lack of knowledge can lead to delays in the delivery of drugs, stockouts, and other disruptions that can have a detrimental effect on patient outcomes. This research project aims to develop a model to predict global supply chain outcomes for essential HIV medicines using machine learning techniques. The critical question of this research is to determine if procurement transaction data can be used to predict delivery delays and estimate the duration of those delays.
This research objective is to develop a model for predicting global supply chain outcomes for essential HIV medicines using machine learning techniques. The objectives of this project are: • To collect and clean a global supply chain data dataset for essential HIV medicines. • To develop a model for predicting global supply chain outcomes using machine learning techniques. • To evaluate the model's performance using accuracy and mean absolute error metrics. • To identify patterns and trends in the data that can be used to optimize the global supply chain for essential HIV medicines.