Date of Award


Document Type

Master Thesis

Degree Name

Masters of Science (Research)


Institute of Technology Tralee

First Advisor

Dr. Pat Doody

Second Advisor

Mr. Andrew Shields


The demand for blood products in Ireland is constantly rising due to population growth and population ageing. It is believed that within the next decade these two factors will present challenges to blood donor recruitment and the availability of blood supplies. Improving the retention of blood donors will have a positive impact on the availability of blood products. Identification of suitable donors with the potential for long-term donating can potentially enhance the predictability of blood supply levels.

This research proposes that the patterns of blood donation behaviours of donors can be isolated from blood donor databases held by blood collecting institutions. These databases typically include only basic information such as age, gender, dates of donations and deferrals from donating. Additionally, the analysis might be enriched with factors related to motivational factors such as intention and attitudes towards blood donation, perceived risks, and personality traits.

Machine learning is the fundamental tool used to analyse these blood donation datasets in an attempt to isolate patterns of donor behaviour and characteristics. It is hypothesised that the patterns discovered can be used to predict an individual’s propensity for blood donation and as a consequence forecast future donations. This analysis attempts to create profiles of different types of donors such as short-term and regular donors, which may help predict the likelihood for individuals to become long-term blood donors.

The experiments completed in this thesis include the application of machine learning algorithms for the purpose of donor classification and the prediction of blood donation behaviours. The datasets used in this study has been kindly provided by the Irish Blood Transfusion Service. Identification of suitable algorithms for profiling of blood donors may aid the forecasting of long-term blood donations and the efficient management of blood stocks. Furthermore, the results of this research may assist policy makers in creating policies to retain future regular donors.

Access Level