Impact of Security Factors in Software Project Risk Assessment using Neural Networks

“software risk” is the measurement of the probability of an unwanted output that could affect the software product’s development process. It always includes the chance of being uncertain and a potential for loss. This paper extends the concepts of Constructive Cost Model (COCOMO) model into fuzzy Expert COCOMO by introducing security factors as additional parameters for the assessment of risk of a software project. This approach is validated with the NASA60 project data and proved that Genetic Algorithm provided efficient risk values with different levels of security parameters. However, in the earlier methods, there was a limitation in effectively dealing with linguistic forms of imprecise and uncertain inputs. This resulted in increase in the cost of designing the mechanisms for security purposes, that formed a major part in the overall cost in the development process of the software product. The risk value of a software project could well be reduced by taking security factors into consideration. The neural network techniques used for validating the risk values are Kohonen neural network, Radial Basis neural (RBF) network, Learning Vector Quantization, Genetic Algorithm(GA). A comparison study has been provided for all the neural network models implemented in order to examine their performances.