Software Effort Estimation using Machine Learning Technique

Software engineering effort estimation plays a significant role in managing project cost, quality, and time creating software. Researchers have been paying close attention to software during the past few decades, great amount of work has done utilizing variety machine-learning techniques algorithms. In order better effectively evaluate predictions, this study recommends various machine learning algorithms for estimating, including k-nearest neighbor regression, support vector decision trees. These methods are now used by development industry estimating with goal overcoming limitations parametric conventional advancing projects. Our dataset, which was created company called Edusoft Consulted LTD, assess effectiveness established method. The three commonly performance evaluation measures, mean absolute error (MAE), squared (MSE), R square error, represent base these. Comparative experimental results demonstrate that trees perform at predicting than other techniques.