Software Cost Estimation Using Open Source GitHub Repositories

This repository contains the outcomes and findings of a master's thesis research conducted at Utrecht University, centered on the topic of software cost estimation. The principal objective was to gather information from open-source repositories on GitHub and utilize this data to predict the cost of software projects.

The published materials encompass four distinct elements:

1. A comprehensive Systematic Literature Review (SLR), containing findings across four primary phases of the research.
2. The Dataset, created over the course of the research, includes information extracted from GitHub repositories.
3. The Code Repository provides the software used to extract data from open-source GitHub projects, along with the machine learning algorithms employed during our research.
4. A detailed Case Study and Experiment data, capturing the empirical investigations undertaken and their subsequent findings.