Weather forecasting is the application of science and technology to predict the state of thernatmosphere for a future time and a given location. Now days, forecasting of accuraternatmospheric conditions is the major challenge for the meteorologist and poor forecasting hasrnsignificant impact on our daily lives. This brings the necessity to make research works onrnforecasting of the weather events with respect to Ethiopia. rnA number of algorithms have been proposed for forecasting of atmospheric condition such asrnsupport vector machine, neural network, numerical, and statistical models. However, in thisrnresearch the design and implementation of weather prediction for the Ethiopian context basedrnon the forecasting ranges using deep neural network, support vector machine for regression,rnand numerical based regression is presented. Four and half yearsâ€™ time series daily and hourly,rntemperature, precipitation, humidity, visibility, dew point, air pressure, and wind historicalrnrecorded data is used from National Oceanic and Atmospheric Administrator (NOAA) tornimplement the system. Since making discussion on all-weather variables makes the report tornlong, forecasting of temperature and precipitation weather variables for Addis Ababa are onlyrnconsidered to be discussed and evaluated as a sample. And their results are examine based onrnpercentage of Root Mean Square Error and time consumption. The same data records arernapplying for all algorithms; and the experimental result shows that, in forecasting of a big data,rnDBN provides a better performance relative to SVM and numerical regressions. In short rangernexperiment we have achieved a forecasting accuracy of temperature 88.6%, 79.6%, and 52.5%rnusing DBN, SVM, and Numerical algorithms respectively. However, if we apply a smallrndimension dataset as input values SVM and numerical regressions completely outperforms thernDBN due to shallow training.