OSS Effort Estimation Using Software Features Similarity and Developer Activity-Based Metrics

Software development effort estimation (SDEE) generally involves leveraging the information about spent in developing similar software past. Most organizations do not have access to sufficient and reliable forms of such data from past projects. As such, existing SDEE methods suffer low usage accuracy. We propose an efficient method for open source software, which provides accurate fast estimates. The significant contributions our article are (i) novel metrics derived developer activity various repositories, (ii) dataset comprising metrics’ values approximately 13,000 GitHub repositories 150 different categories, (iii) tool based on a description similarity model . Our is basically machine learning trained using PVA product descriptions repositories. Given newly envisioned yields estimate it. achieves highest standardized accuracy score 87.26% (with Cliff’s δ = 0.88 at 99.999% confidence level) 42.7% with automatically transformed linear baseline model. artifacts available https://doi.org/10.5281/zenodo.5095723.