DOI: 10.17587/prin.13.322-330

Applying Supervised Machine Learning Methods to Determine the Atomicity of Requirements for Complex Technical Systems

K. I. Gaydamaka, k.gaydamaka@gmail.com, Department of Systems Engineering, MIREA — Russian Technological University, Moscow, 119454, Russian Federation, P. A. Ognyanovich, Pasha2la71@gmail.com, National Research Nuclear University MEPhI

Corresponding author: Kirill I. Gaydamaka, Senior Lecturer, Department of Systems Engineering, "MIREA — Russian Technological University", Moscow, 119454, Russian Federation, E-mail: k.gaydamaka@gmail.com

The article is devoted to the problem of determining the atomicity of requirements for complex technical systems. The purpose of this article is to apply supervised machine learning methods, namely classification, to determine the atomicity of requirements. It is assumed that feature engineering based on the linguistic features of requirements state­ments will make it possible to classify requirements into atomic and non-atomic ones with high accuracy. The article describes the use of the following methods for generating features: fastText, BERT, customFeature. Requirements are classified using a logistic classifier, decision trees, random forest, and gradient boosting. The best combination of methods turned out to be using customFeature with gradient boosting.

Keywords: gradient boosting, BERT, requirements management, machine learning, requirements atomicity, requirements quality

pp. 322—330

For citation:
Gaydamaka K. I., Ognyanovich P. A. Applying Supervised Machine Learning Methods to Determine the Atomicity of Requirements for Complex Technical Systems, Programmnaya Ingeneria, 2022, vol. 13, no. 7, pp. 322—330.

The article is based on the materials of the report at the Seventh International Conference "Actual problems of Systems and Software Engineering" APSSE 2021.