Road traffic accidents are among the top le a din g causes of deaths and injuries of variousrnlevels. Ethiopia is one of the countries of the world experiencing highest rate of suchrnaccident s resulting in fatalities and various levels of injuries. Addis Ababa, the capital city ofrnEthiopia, takes the lion 's s hare of the risk having higher number of vehicles and traffic. Andrnthe cost of these fatalities and injuries due to such road traffic accidents has a great impact onrnthe socio-economic development of a society.rnThis thesis reports on the finding s of a research that had the objective to build a decisionrnsupport sys tem to handle road traffic accident analysis, for Addis Ababa C it y Traffic Office.rnThe study focused o n injury severity levels resulting from an accident. In do in g so the aim ofrnthis research was to assess the potential applicability of data mining technology specificallyrndecision tree technique to help traffic accident data analysis in decision-making process at therntraffic office.rnIn the thesis, the process of building a model through know ledge discovery and data miningrntechniques on historical accident record data is described. Different tools and techniques arernalso used for the purpose of data analysis. The methodology adopted had three basic stepsrnname Lydia collection , data preparation, and model building and validation. The required datarnwas selected and extracted from Addis Ababa Traffic Office. Then, data preparation tasksrn(such as data transformation, deriving of new attributes, and handling o f missing values) werernundertaken. The final step was mo del building and validation using the selected tools andrntechniques.rnThe decision tree Knowledge SEEKER algorithm is used in the stud y. The particular too l usedrnfor the mo de l building was the decision tree incorporated in Knowledge STUDIO. Afterrnsuccessive experiments, a model that can classify accidents w ell with a better accuracy asrnfatal , serious, and slight or property-damage was selected and evaluated . Experiment result srnreveal that the use o f decision tree is helpful in detecting dangerous accidents throughrnidentifying behavioral and roadway accident patterns. The reported findings are promising,rnmaking the proposed model a useful" tool in the decision making process. And the wholernresearch process can be a good input for further in-depth research.