Predict Software Reliability by Support Vector Machine

Md. Baharul Islam
Department of Multimedia Technology and Creative Arts
Daffodil International University
Md. Kamrul Hasan
Project Manager
Atomix System Limited Dhaka
A. H. M. Saiful Islam
Department of Computer Science and Engineering


The application of computer system has now crossed many different fields. Software has become an essential part of many industrial, military and even commercial systems. We may find programs containing millions of lines of code in both microcomputers and supercomputers. Software reliability is an important research area because of safety critical system. In this paper, a model that can be used for software reliability prediction is explored. The proposed model is implemented using Support Vector Machine (SVM) and has been applied on a custom set of test data. It focused on a particular dataset behavior in predicting reliability. Focusing on a particular dataset behavior is performed to develop an accurate model since the recent work focused on developing a model which can be more accurate. We also build a SVM model to find the relationship between reliability and error rate.