A Software Defect-Proneness Prediction Framework: A new approach using genetic algorithms to generate learning schemes

Abstract

Recently, defect prediction software is an important research topic in the software engineering field. The demand for development of good quality software has seen a rapid growth in the last few years. The software measurement data collected during the software development process include valuable information about software projects status, progress, quality, performance, and evolution. The software fault prediction in the early phases of software development can help and guide software practitioners to focus the available testing resources on the weaker areas during the software development. OBJECTIVE: This paper presents an approach that combines three phases: data preprocessing, attribute selector and learning algorithms using a genetic approach and select the best combination. METHOD: The framework is comprised of 1) scheme learning generator. This component evaluates performance of the learning schemes and suggests the best option according to each data set analyzed, 2) defect predictor component builds models according to the evaluated learning schemes and predicts software defects with new data agreed to the constructed model. CONCLUSIONS: The framework has considered more combinations of learning schemes than other proposals which select the model configuration manually, which means that there are more possibilities to find better learning schemes for each data set. The computational processing of the genetic approach was less costly than Song approach. Finally, The Genetic approach presented an improvement of 0.032 equivalent to 3.2% more than Song approach.

Static test flakiness prediction: How Far Can We Go?

“…This set is composed of ten factors measuring the size and complexity of production and/or test code. Some of these metrics belong to the Object-Oriented metric suite proposed by Chidamber and Kemerer (Chidamber and Kemerer 1994), e.g., coupling between object classes (CBO), while other metrics come from other catalogs, e.g., the McCabe cyclomatic complexity (McCabe 1976) or the Halstead's metrics (Murillo-Morera and Jenkins 2015). The rationale behind the selection of these metrics was driven by our willingness to verify whether large and/or complex code might have an impact on the likelihood of observing a flaky behavior of the test case.…”

An Automated Defect Prediction Framework using Genetic Algorithms: A Validation of Empirical Studies

“…The main goal in generating these predictions is to enable software engineers to focus development and testing activities on the most fault-prone parts of their code, thereby improving software quality and making a better use of limited time and resources [16] and [1]. The study and construction of these techniques have been the emphasis of the fault prediction modeling research area and also the subject of many previous research projects [12], [22], [23], [33] and [37].…”