V.A. Galkin – Ph.D. (Eng.), Associate Professor,

Information Processing and Control Systems Department, Bauman Moscow State Technical University

E-mail: galkin@bmstu.ru I.S. Biushkin − Master,

Information Processing and Control SystemsDepartment, Bauman Moscow State Technical University

E-mail: biushkin.iwan@yandex.ru

U.V. Zhuravleva − Master,

Information Processing and Control Systems Department, Bauman Moscow State Technical University

E-mail: 3101zuv@mail.ru

In developing software products, with each new technological addition, software complexity increases. Reproduction and elimination of defects and errors in the code requires more and more time resources. The current state of analytics tools allows you to explore only the static aspects of software development. Nevertheless, the problem arises of assessing the process of dynamic development of the system in order to timely detect erroneous components and modules in the early stages of development. The aim of this work is to improve the forecasting of system defects, based on an analysis of the current state of the program code and previous versions of the project. The data obtained are modeled using four ensemble classifiers to calculate the trend of defects in a future software release. The results demonstrate the superiority of the Voting algorithm (VA) in solving the problem of forecasting defects compared to other algorithms: Gradient Boost (GB), Random Forest (RF) and Bagging (BA).

1. Malhotra R., Shukla S., Sawhney G. Assessment of defect prediction models using machine learning techniques for object-oriented systems. In 2016 5th International Conference on Reliability, Infocom Technologies and Optimization. Sep 2016. P. 577–583.
2. Gyimothy T., Ferenc R., Siket I. Empirical validation of object-oriented metrics on open source software for fault prediction. IEEE Transactions on Software Engineering. Oct 2005. C. 897–910.
3. Chidamber S.R., Kemerer C.F. A metrics suite for object oriented design. IEEE Transactions on Software Engineering. June 1994.  P. 476–493.
4. Yuming Zhou, Hareton Leung. Empirical analysis of object-oriented design metrics for predicting high and low severity faults. IEEE Transactions on Software Engineering. Oct 2006. P. 771–789.
5. Yogesh Singh, Arvinder Kaur, Ruchika Malhotra. Empirical validation of object-oriented metrics for predicting fault proneness models. Software Quality Journal. March 2010. P. 3–35.