A Methodology for Software Cost Estimation Using Machine Learning Techniques: International conference on Recent Trends in Artificial Intelligence, IOT, Smart Cities & Applications (ICAISC-2020)

Abstract

Now a day’s many different organization expends billions of dollars on software development and maintenance annually. Many organization software projects are fail to be completed, or it is over budget, due to the inability of current software cost-estimation techniques to estimate effort and cost, at early venture organize, the degree of exertion required for an undertaking to be finished. One explanation is that present programming cost-estimation models will in general perform ineffectively when applied outside of barely characterized spaces. Machine learning offers an elective way to deal with the present models. In Machine learning, the area explicit information and the computer can be coupled to make a motor for information revelation. Using genetic programming, neural networks and genetic algorithms, alongside a distributed programming project data set. Several cost estimation models were developed. Testing was conducted using a COCOMO 81 data set. Every one of the three procedures demonstrated degrees of execution that show that every one of these systems can furnish software project managers with capacities that can be utilized to get better software cost estimates.