Large software products require high effort to maintain the code base. Most of the time managers face challenging situations for efficient allocation of resources. In this paper, we proposed a novel approach to aid the software engineering managers to predict the software defects using few matrices. In our study, we have used publicly available software engineering repositories concentrating on object-oriented (OO) methodology. Our study suggests that few important matrices are sufficient to predict the defects in the system. We have used kNN classifier for classification and random subset feature selection (RSFS) for dimensionality reduction of the attributes.
CITATION STYLE
Ramana Rao, G. N. V., Balaram, V. V. S. S. S., & Vishnuvardhan, B. (2019). Attribute reduction for defect prediction using random subset feature selection method. In Advances in Intelligent Systems and Computing (Vol. 862, pp. 551–558). Springer Verlag. https://doi.org/10.1007/978-981-13-3329-3_52
Mendeley helps you to discover research relevant for your work.