The forecasting of blood supplies is a serious and recurrent problem for blood collection managers. In January 2019, "Nationwide, the Red Cross saw 27,000 fewer blood donations over the holidays than they see at other times of the year." Machine learning can be used to learn the patterns in the data to help to predict future blood donations and therefore save more lives.

In this Project, we use data collected from the donor database of Blood Transfusion Service Center in Hsin-Chu City, Taiwan. The center passes its blood transfusion service bus to one university in Hsin-Chu City to gather blood donated about every three months. The dataset, obtained from the UCI Machine Learning Repository, consists of a random sample of 748 donors. From this we predict if a blood donor will donate within a given time window. We also look at the full model-building process: from inspecting the dataset to using the tpot library to automate your Machine Learning pipeline.