I.J. Information Engineering and Electronic Business, 2021, 3, 39-48 Published Online June 2021 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijieeb.2021.03.05 Copyright © 2021 MECS I.J. Information Engineering and Electronic Business, 2021, 3, 39-48 Predicting the Behavior of Blood Donors in National Blood Bank of Ethiopia Using Data Mining Techniques Teklay Birhane, Brhanu Hailu Department of Information Science, Mekelle University, Tigray, Ethiopia Email: {teklaybirhane12, brhanuhaylu}@gmail.com Received: 14 March 2020; Accepted: 24 June 2020; Published: 08 June 2021 Abstract: A modern technology used for extracting knowledge from a huge amount of data using different models and tasks such as prediction and description is called data mining. The data mining approach has a great contribution on solving a different problem for data miners. This paper focuses on the application of data mining in health centers using different models. The model development process helps to identify or predict the behavior of blood donors whether they are eligible or ineligible to donate blood by their right status way and protects any blood bank health center from the collection of unsafe blood. Classification techniques are used for the analysis of Blood bank datasets in this study. For continuous blood donors, it will help to enable to donate voluntary individuals and organizations systematically. J48 decision tree, neural network as well as naïve Bays algorithms have been implemented in Weka to analyze the dataset of blood donors. The study is used to classify the blood donor's eligibility or ineligibility status based on their genders, deferral time, weight, age, body priced, tattoos, HIV AIDS, blood pressure, donation frequency, hepatitis, illegal drug use attributes. From the 11 attributes, gender does not affect the result. We have used 1502 datasets for the train set and 100 datasets for testing the model using cross-fold validation. Cross-fold data, partition was used in this study. The efficiency and effectiveness of the algorisms are measured automatically by the system. The obtained result showed that the J48 classifier outperforms the best result as well as both neural network and navies, Bayes, in terms of matrix evolution, with its 97.5% overall model accuracy has offered interesting rules. Index Terms: Data Mining, Blood Donation, Classification, Decision Tree, Neural Network, and Navies Bayes. 1. Introduction The process of finding information from large repositories through the manual system is difficult nowadays since data size has increased at alarming times. A computer-based method has been applied to find necessary information from data warehouses, repositories in which data is available such as business organizations whether internet-based or offline. Based on that data mining have conceptualized, in the 1990s as a means of analyzing a vast amount of data that is available in different organizational repositories such as healthcare, education system, market places, and governmental offices[1]. Data mining is an automatic knowledge discovery process from immense databases in a given application and its main-goal is to find out hidden and interesting information, patterns, and useful knowledge [2]. As blood banks has massive volume of data, the use of data mining techniques is necessary to analyze and convert them into useful and interesting knowledge. Therefore, the researchers used data-mining techniques for predicting continuous behavior of healthy blood donors in the Ethiopian national blood bank in the case of the Harari branch. The main aim of predicting blood donor’s behaviors is to know and gather relevant information about the donor’s health status and group under continuous giving blood for a blood bank in the proper way. Currently in Ethiopia, an urgent need for blood is growing at an alarming rate as the number of medical surgeries, accidents and health diseases is growing on increasing rate. There is too few number of blood donors in Ethiopia. Because of that, the Ethiopian National Blood Bank falls to crucial issues of blood shortage and unsafe blood collection. Those problems leads to death and serious bad health consequences. Since the behavior of blood donors is unknown, it is becoming too difficult to extract information using conventional database techniques to solve such kinds of a serious problem. In fact, that the researchers stand to conduct the study using data mining techniques to predict the continuous behavior of blood donors in the case of the Harar branch. The main objective of this study is to predict the behavior of blood donors in the national blood bank of Ethiopia as eligible or ineligible to donate using data-mining techniques to extract useful information, generate new patterns and knowledge that helps to collect safe blood and increase the number of blood donors in Ethiopia.