A PREDICTION MODEL TO IDENTIFY EFFECTIVE CONFLICT RESOLUTION METHOD

SEBLEWONGEL, HABTEMICHEAL

dc.contributor.author	SEBLEWONGEL, HABTEMICHEAL
dc.date.accessioned	2022-11-16T11:18:24Z
dc.date.available	2022-11-16T11:18:24Z
dc.date.issued	2022-07
dc.identifier.uri	http://ir.bdu.edu.et/handle/123456789/14398
dc.description.abstract	A major disagreement or argument, usually one that lasts a long time, is referred to as conflict or it is simply creating a difference between the two parties. Conflict will always exist in society, with the causes ranging from personal, cultural, class, status, political, and international. Academic recognition may or may not be a relevant motivator in a conflict that is emotional, intellectual, or theoretical. There are five major conflict resolution styles. Collaboration, Competition, Avoidance, Accommodation, and Compromise are only a few styles. However, most conflicts discovered in organizations are increasing around the world, particularly in low-income countries(LICs) like Ethiopia, due to a lack of conflict resolution approaches that do not examine the organizations and conflict circumstances. This research aims to develop a machine-learning model for the prediction of effective conflict handling or resolution methods in Technical Vocational Educational and Training (TVET) colleges. This study followed experimental methodology employed using anaconda environment python programming Jupyter notebook. The machine-learning approach is employed by collecting the data from Amhara National Regional State Job & Training Bureau and their branches namely Bahirdar, Woreta, and Debretabor TVET colleges. The study used about five machine learning algorithms including Support Vector Machine (SVM) , Decision Tree(DT) , Naïve Bayes(NB), K-Nearest Neighbors (KNN), and Logistric Regeression (LR). The study analysis result a classification accuracy of SVM 92.52%, DT 92.34%, NB 92.25%, KNN 91.37% and LR 92.16%. that the study findings showed that SVM outperformed better than the other machine learning algorithms. This is because SVM works better for categorical and high dimensional data. Keywords: DT, KNN, LR, SVM, TVET	en_US
dc.language.iso	en_US	en_US
dc.subject	FACULTY OF COMPUTING	en_US
dc.title	A PREDICTION MODEL TO IDENTIFY EFFECTIVE CONFLICT RESOLUTION METHOD	en_US
dc.type	Thesis	en_US