Parametric Influence Detection for Software Projects and Success Classification using Machine Learning

Abstract

Ensuring the success of software projects is a critical concern for software development organizations. Several factors, including project complexity, team experience, and customer satisfaction, contribute to the success of software projects. Identifying the key factors that influence software project success is an essential step towards achieving project success. In this paper, we propose a machine learning-based approach for parametric influence detection in software project success classification. The proposed approach integrates feature selection, feature engineering, and classification using a proposed machine learning method. The approach leverages the power of machine learning to identify the most significant parameters that influence software project success. To evaluate the effectiveness of our approach, we conducted an empirical study on a stack overflow dataset comprising more than 1400 software projects. We compared the performance of our proposed approach with many other recent research outcomes on machine learning methods. The results of our study demonstrate that our proposed approach achieves a classification accuracy of 98.76%, outperforming the recent research outcomes. Our approach also identified the top five parameters that influence software project success. Our proposed approach can also be extended to other domains beyond software development, such as healthcare and finance, where parametric influence detection is critical for decision-making. Finally, our proposed machine learning-based approach for parametric influence detection in software project success classification demonstrates superior performance compared to state-of-the-art methods. This approach can be used by software development organizations to improve their project success rates and make informed decisions about project planning and resource allocation.