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 this study, machine learning algorithms were investigated in conjunction with feature transformation, feature selection, and parameter tuning techniques to estimate the development effort accurately and a new model was proposed as part of an expert system. We preferred the most general-purpose algorithms, applied parameter optimization technique (Grid- Search), feature transformation techniques (binning and one-hot-encoding), and feature selection algorithm (principal component analysis). All the models were trained on the ISBSG datasets and implemented by using the scikit-learn package in the Python language. The proposed model uses a multilayer perceptron as its underlying algorithm, applies binning of the features to transform continuous features and one-hot-encoding technique to transform categorical data into numerical values as feature transformation techniques, does feature selection based on the principal component analysis method, and performs parameter tuning based on the GridSearch algorithm. We demonstrate that our effort prediction model mostly outperforms the other existing models in terms of prediction accuracy based on the mean absolute residual parameter.

Software Project Management Using Machine Learning Technique—A Review

“…This section describes articles that used Artificial Neural Networks (ANNs). Two articles [90,91] on the establishment of ML risk stimulator systems offer the most appropriate risk incentives on requirements, scenarios, and taxonomy tags for the creation of a software project. The study should be viewed independently of any of these taxonomies, since the taxonomies are independent of the danger causes.…”

Yapay Zeka Teknikleri Kullanılarak Proje Üretim Sistemlerinin Tasarımı ve Geliştirilmesi

“…Ertuğrul ve ekibi (2019) makine öğrenme algoritmalarını, proje geliştirme sürecinde belirlenmesi gereken insan kaynakları, bütçe, personel sayısı, proje planları ve programları gibi özellikleri daha yüksek doğrulukla tahmin etmek için var olan özelliklerinin dönüştürülmesi, seçimi ve parametrelerinin belirlenmesi için gerekli olan teknikleri ile incelenmiş ve uzman sistemin bileşeni olarak yeni bir model ortaya koymuştur. Ekip veri kümeleri üzerinde çalışırken Python dilinde scikitlearn paketini kullanılmıştır [16].…”

Measuring Software Maintainability with Naïve Bayes Classifier

“…This technique is used to estimate software cost by examining data of software engineering. In the study [ 31 ] conducted by Ertugrul et al, several algorithms of machine learning were examined with feature transformation, feature selection, and also with the techniques of parameter optimization. They introduced a new model which provides improved effort estimation by considering the artificial neural networks (ANN) specifically “multilayer perceptron topology”.…”