DOI: 10.4018/IJAEC.2020010104 International Journal of Applied Evolutionary Computation Volume 11 • Issue 1 • January-March 2020 Copyright © 2020, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. 52 An Empirical Evaluation of Assorted Risk Management Models and Frameworks in Software Development Alankrita Aggarwal, IKG Punjab Technical University, Jallandhar Punjab, India https://orcid.org/0000-0002-0931-1118 Kanwalvir Singh Dhindsa, Baba Banda Singh Bahadur Engineering College, Fatehgarh Sahib Punjab, India https://orcid.org/0000-0002-7911-9244 P. K. Suri, Kurukshetra University, Kurukshetra, India ABSTRACT Software risk management is one the key factors in software project management with the goal to improve quality as avoid vulnerabilities. The term defect refers to an imperfection that may arise because of reasons including programmers’ skills, lack of suitable testing strategies, and many others. When actual results are different from expected result or meeting wrong requirement, it is called defect and it forms the basis of risk escalation in a software project which is obviously not accepted in any type of deployment. Making a reliable software should be risk free from any vulnerability. Along with reliability another issue arises is software quality which is a factor with software risk management. The quality of software is to reduce the occurrence of risks and defects with the objective to produce an effectual value software which is key point of consideration. In this article, is underlined the present assorted risk management strategies proposed and projected by a number of researchers and academicians on the different parameters using benchmark datasets from renowned sources of research. KEywoRDS Software Defects and Risks, Software Risk Management, Software Risk Management Mechanisms, Software Risk Management Models 1. INTRoDUCTIoN Software defect prediction (Fenton & Neil, 1999) in software engineering used to predict the deformity in the software module. Numbers of defect are present during the development or after the delivery of software module (Sullivan & Chillarege, 1991). To obtain high quality software the prediction process is followed to predict to the defects. The need of obtaining high quality software is to gain customer loyalty. Few big organizations are using this prediction process as they release their software and software versions frequently and they have less time so instead of manually predicting the defects they use software deformity process. Few techniques like decision tree, fuzzy logic, artificial neural network, Random Forest, HoneyBee Algorithm, and Bat Algorithm etc. are used for Software defect prediction. In proposed method, the artificial neural network is applied which produces more precise result then the existing on (Mittal, Sharma, Singh et al., 2019).