Software Development Effort Estimation Using Relational Database and Optimized Learning Mechanism

Accurately estimating the cost of software development is crucial for effective project planning and resource allocation. However, traditional estimation methods rely heavily on expert judgment historical data, which can be time consuming prone to errors. This study suggests a learning-based model that leverages relational databases improve accuracy. The proposed approach estimates based effort required complete development, key driver cost. designed address challenges posed by variability in open-source including variable team sizes, working hours, expertise. collects pre-processes data from platforms selects drivers metrics logical rules SQL queries. Moreover, we propose an optimized Artificial Neural Network (ANN) with augmented topology automate selection neuron units, layers, adjustment learnable parameters according input variables. evaluated 100 repositories dataset demonstrates its effectiveness accurately system implemented using Python performance such as MSE, RMSE, MAE, MMRE. Results indicate our offers more accurate efficient estimation, especially freelancers outsourcing firms. has potential save resources reliability accuracy estimation.