Weather forecasting has become important now a day because of varying climatic conditions around the world. Many technologies have been introduced to predict the weather whose accuracy is around 70%.Weather forecasting is used in machine learning. It is a powerful technique to predict the weather with more accuracy. Weather dataset is collected and analysed and algorithms on it to predict the weather. Using a Back Propagation Neural Network the error rate becomes less and many factors that are involved to predicting the weather gives the accurate results. To compare and evaluate the performance of above model and the programming was carried out using Visual Studio as a tool.