Print Email Facebook Twitter Data-Driven Extract Method Recommendations: A Study at ING Title Data-Driven Extract Method Recommendations: A Study at ING Author van der Leij, David (Student TU Delft; ING) Binda, J.R. (ING) van Dalen, Robbert (ING) Vallen, Pieter (ING) Luo, Yaping (Eindhoven University of Technology; ING) Aniche, Maurício (TU Delft Software Engineering) Contributor Spinellis, Diomidis (editor) Date 2021 Abstract The sound identification of refactoring opportunities is still an open problem in software engineering. Recent studies have shown the effectiveness of machine learning models in recommending methods that should undergo different refactoring operations. In this work, we experiment with such approaches to identify methods that should undergo an Extract Method refactoring, in the context of ING, a large financial organization. More specifically, we (i) compare the code metrics distributions, which are used as features by the models, between open-source and ING systems, (ii) measure the accuracy of different machine learning models in recommending Extract Method refactorings, (iii) compare the recommendations given by the models with the opinions of ING experts. Our results show that the feature distributions of ING systems and open-source systems are somewhat different, that machine learning models can recommend Extract Method refactorings with high accuracy, and that experts tend to agree with most of the recommendations of the model. Subject Machine Learning for Software EngineeringSoftware EngineeringSoftware Refactoring To reference this document use: http://resolver.tudelft.nl/uuid:4470f6e1-6e3b-4112-86a3-dbe9a421aec3 DOI https://doi.org/10.1145/3468264.3473927 ISBN 978-1-4503-8562-6 Source ESEC/FSE 2021 - Proceedings of the 29th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering Event ESEC/FSE 2021: 29th ACM Joint EuropeanSoftware Engineering Conference and Symposium on the Foundations of SoftwareEngineering, 2021-08-23 → 2021-08-28, athens, Greece Series ESEC/FSE 2021 - Proceedings of the 29th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering Part of collection Institutional Repository Document type conference paper Rights © 2021 David van der Leij, J.R. Binda, Robbert van Dalen, Pieter Vallen, Yaping Luo, Maurício Aniche Files PDF 3468264.3473927.pdf 636.06 KB Close viewer /islandora/object/uuid:4470f6e1-6e3b-4112-86a3-dbe9a421aec3/datastream/OBJ/view