Assessment of Breastfeeding practices in Ethiopia using different data mining techniques

Abstract

Breastfeeding is one of the critical issues in Ethiopia because researches show that 24.0% - 27.0% of infant death in Ethiopia is due to poor breastfeeding practices. UNICEF has been reported that a good promotion of breastfeeding practices is a most important strategic plan to reduce child mortality in developed and developing countries. Hence, it is important to identifying the determinate factors of poor breastfeeding practice, especially poor countries like Ethiopia. Poor Breastfeeding is a reasonable well-defined problem caused by many factors that are related to motherhood, environment, community and child. Therefore, it is very important to predict the determinate factors of poor breastfeeding practice in various communities in the country in order to come up with feasible intervention strategies to minimize the problem. This research intends to provide a survey of current techniques of knowledge discovery in large databases using data mining techniques which will be useful for medical practitioner to improve the breast feeding practices. The assessment was carried out with cross validation and percentage split of different data mining algorithms such as decision tree, Naive Bayes , Artificial Neural Network and Bagging.