Bekele, Rahel (PhD)Abrar, Mohammed2020-06-122023-11-182020-06-122023-11-182009-01http://etd.aau.edu.et/handle/12345678/21562The identification of causes and phenomena associated with crime is one of the mo s t popular goals in criminology, especially in view of its practical value and the belief that such identifications are useful w hen seek in g to correct or control criminal behavior. The utility of discovering causes must, however, be qualified. Understanding and processing of offenders' record s is one method to learn about both crime and the individuals who in valve in misdeeds so that police can take crime prevention measures accordingly. Though data on criminals are continuously being gathered, the y are not effectively being utilized for extract ting pattern s that can be used for effective management of crimes. This is mainly due to the inadequacy of the human brain to search for complex and multifactor depend envies in data an d the lack of objectiveness in such analysis demanded a computerized approach. Developments in the inform at ion and communication tech neologies have made it possible for organizations to collect, s tore and maniple ate massive amount of data. One such development is Bayesian Network. In this study, the main objective of the research is to develop a predictive model for factors that constitute higher crime trend s in Addis Ababa which makes use of Bayesian Network modeling techniques. For this purpose, published literature's in related areas have been studied together with the review of different Bayesian Network modeling app roaches . Different to oils and techniques supporting such task were examined by taking into co n side ration the reapplication to the problem domain. In addition, an experiment is conducted to explore the potential of Bayesian network in modeling factors that constitute higher came trend using personal identification record of criminals. For the purpose of the experimentation o n 1572 criminal reco rd s were collected from the Addis Ababa Police Commission. The record s were manually and automatically y further p reprocessed to make them compatible with software used. Important attributes that are considered relevant for the construct in g predictive model for higher crime trends were selected. After p reprocessing the data, alearnin g classifier is used to learn from the training data and use this classifier to class if yew data. A model is constructed for the best learned model from data. Based on the experimental data, a Bayesian performance prediction model was developed where 73.25 % prediction accuracy was fir stobse rved . Further experiments and modification of the prediction model in creased the level of prediction accuracy to 75.78 %. Fin all y, Three Phase Dependency Analysis in particular and Bayesian network in general is found applicable for modeling determinant factors for higher crime trends.enInformation ScienceThesis