Air pollution has an enormous influence on the number of constituents in the atmosphere that leads to effects like global warming and acid rains. The main cause of pollution is hazardous gases from the traffic system with a large number of vehicles. The challenge in the city is high because of cars and industries smoke. On the other hand, people demanding pure air for their life. The purpose of this study is to improve the effectiveness of environmental air pollution risk analysis through the application of data mining. To achieve this objective, the KDD method and data mining technique is utilized to model the air pollution dispersion in Addis Abeba City. Factors that are influencing the predicted value consist of weather-related and air pollution-related data, i.e. wind direction, wind speed, relative humidity, temperature, and PM2.5 as target values. Daily meteorological forecast variables as well as the respective pollutant predictors were used as input to a multi-layer perceptron (MLP) type of feed-forward back-propagation neural network to predict the classify data based on the Environmental protection agency guidelines. Two years of hourly data including temperature, Relative Humidity, Wind Speed, Wind Direction, and PM2.5 were used as inputs to the artificial neural networks. From 51951 data, 36371 of data were used to train the models and the rest of the data were applied to test the models. The results of using artificial neural networks indicated that the preferred models performed MSE=0.022587 and R= 96 in predicting air pollution concentrations. This helps in the prediction of air quality in the city Addis abeba and this could serve as an important reference for government agencies in evaluating present and devising future air pollution policies.