Performance tuning for machine learning-based software development effort prediction models

Abstract

Software development effort estimation is a critical activity of the project management process. In thisstudy, machine learning algorithms were investigated in conjunction with feature transformation, feature selection, andparameter tuning techniques to estimate the development effort accurately and a new model was proposed as part ofan expert system. We preferred the most general-purpose algorithms, applied parameter optimization technique (GridSearch), feature transformation techniques (binning and one-hot-encoding), and feature selection algorithm (principalcomponent analysis). All the models were trained on the ISBSG datasets and implemented by using the scikit-learnpackage in the Python language. The proposed model uses a multilayer perceptron as its underlying algorithm, appliesbinning of the features to transform continuous features and one-hot-encoding technique to transform categorical datainto numerical values as feature transformation techniques, does feature selection based on the principal componentanalysis method, and performs parameter tuning based on the GridSearch algorithm. We demonstrate that our effortprediction model mostly outperforms the other existing models in terms of prediction accuracy based on the meanabsolute residual parameter.