The blood management system confronts a challenge with blood transfusions and their distribution regardless of the efforts of the World Health Organization and other global health organizations: inadequate supply, excessive demand, and a shortage of accessible blood. Due to its ability to raise labor efficiency and service quality via systematic management, artificial intelligence is currently necessary to enhance blood supply operations. The objective of this work is to provide an AI/ML platform that facilitates the use of data to assist health professionals in making the most effective management choices that are consistent with methods for minimizing waste and costs. By more accurately anticipating blood demand. As production models, we are using both time series and machine learning methods as prediction models. The optimal performance model for the provided case study was determined by comparing the performance outcomes of each method. In this work, autoregressive Moving Average models, autoregressive Integrated Moving Average models, and seasonal ARIMA models are applied. In addition, we used four native algorithms for machine learning: Artificial Neural Networks, Linear Regression, and Support Vector Regression. The results demonstrate that both types of forecasting models can significantly enhance the management of the blood supply.