Software effort and risk assessment using decision table trained by neural networks

Software effort estimations are based on prediction properties of system with attention to develop methodologies. Many organizations follow the risk management but the risk identification techniques will differ. In this paper, we focus on two effort estimation techniques such as use case point and function point are used to estimate the effort in the software development. The decision table is used to compare these two methods to analyze which method will produce the accurate result. The neural network is used to train the decision table with the use of back propagation training algorithm and compare these two effort estimation methods (use case point and function point) with the actual effort. By using the past project data, the estimation methods are compared. Similarly risk will be evaluated by using the summary of questionnaire received from the various software developers. Based on the report, we can also mitigate the risk in the future process.