Akademik Veri Yönetim Sistemi
Healthcare facilities, one of the most important social services, play a critical role in providing medical services. Service disruption or poor quality at these facilities can occur because of the lack of, or challenges in, the inventory management systems of such facilities. In this research, it is aimed to solve these challenges by developing a strategy for optimizing inventory management through the application of classification methods in the field of computer science. A solution for inventory management of healthcare facilities has been developed using up-to-date and valid Machine Learning techniques. Before the classification process with machine learning, some preprocessing operations were applied to the dataset. The machine learning models such as Logistic Regression, Decision Tree, Naive Bayes, Random Forest, K-Nearest Neighbors (KNN), Neural Network, XGBoost and Support Vector Machine were used to process and analyze the data collected in healthcare facilities. Google Colab environment was selected as the application computing environment and Python programming language was used for coding. Different machine learning algorithms were run for the classification of basic materials in the inventory and their performances were evaluated based on the results. According to the performance outputs of the algorithms, it was determined that Decision Tree, KNN, Random Forest and XGBoost algorithms performed better than other algorithms in classification tasks. The effectiveness of inventory management, which, in turn, may have a direct impact on the quality of services and efficiency of healthcare facilities, is the fundamental issue of concern to both the providers of healthcare services and the recipients of the services. The application of machine learning methods, namely Decision Tree, Random Forest, KNN, and XGBoost, which are revealed in this study as highly efficient, can improve classification procedures of inventory and create a more balanced and effective system in healthcare facilities.
