Enhancing Human Aspect of Software Engineering using Bayesian Classifier

TL;DR

This paper uses a Bayesian classifier to analyze human performance data in software engineering, aiming to improve project quality and reduce failure rates by selecting competent personnel.

Contribution

It introduces a novel application of Bayesian classification to assess project personnel skills and predict their impact on software project success.

Findings

Bayesian classifier effectively captures human performance patterns.

Improved personnel selection reduces project failure rates.

Enhanced project outcomes through data-driven personnel assessment.

Abstract

IT industries in current scenario have to struggle effectively in terms of cost, quality, service or innovation for their subsistence in the global market. Due to the swift transformation of technology, software industries owe to manage a large set of data having precious information hidden. Data mining technique enables one to effectively cope with this hidden information where it can be applied to code optimization, fault prediction and other domains which modulates the success nature of software projects. Additionally, the efficiency of the product developed further depends upon the quality of the project personnel. The position of the paper therefore is to explore potentials of project personnel in terms of their competency and skill set and its influence on quality of project. The above mentioned objective is accomplished using a Bayesian classifier in order to capture the pattern of human performance. By this means, the hidden and valuable knowledge discovered in the related databases will be summarized in the statistical structure. This mode of predictive study enables the project managers to reduce the failure ratio to a significant level and improve the performance of the project using the right choice of project personnel.