Comparative Study Between Machine Learning Algorithms Applied to Support QA Contracting Processes - Algorithm Comparison

Aug 2, 2026

Upload by Levi

A comparative study evaluates multiple machine learning algorithms for their suitability in Quality Assurance (QA) contracting procedures, following the Knowledge Discovery Database (KDD) methodology. Nearest Neighbors, Linear SVM, Radial SVM, Gaussian Process, Decision Tree, Neural Network, Logistic Regression, Naive Bayes, and QDA are assessed using metrics such as F1-Score, recall, accuracy, and AUC-ROC, alongside learning curves, boundary maps, confusion matrices, MCC, and complexity curves. Results indicate Neural Network, QDA, and Gaussian Process achieve strong performance and comprehensive evaluation, while Nearest Neighbors and Linear SVM are suboptimal, motivating adaptation and improvement.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Introduction

Problem

Comparative Study Between Machine Learning Algorithms Applied to Support QA Contracting Processes David Santiago Bejarano Velandia, Jorge Enrique Rodriguez Rodriguez, and David Stevens Gonzalez Lizarazo Abstract—This study comprehensively compares different machine learning algorithms to assess their applicability in Quality Assurance (QA) contracting procedures. The evaluated algorithms encompass Nearest Neighbors, Linear SVM, Radial SVM, Gaussian Process, Decision Tree, Neural Network, Logistic Regression, Naive Bayes, and QDA. Following the Knowledge Discovery Database (KDD) process, the methodology includes a diverse set of evaluation metrics such as F1-Score, recall, accuracy, and AUC-ROC, as well as learning curves, boundary maps, confusion matrices, Matthews Correlation Coefficient (MCC), and complexity curves. According to the Gartner Magic Quadrant assessment, the results suggest that Neural Network, QDA, and Gaussian Process models exhibit strong performance and thorough evaluation, making them optimal for the case study presented in the paper. In contrast, Nearest Neighbors and Linear SVM models are considered suboptimal, indicating an opportunity to explore the reasons behind their behavior in the case study and how to modify them for improved results. The other algorithms also present various possibilities for adaptation to the current case study, either as models with limited analysis or as imprecise models that can offer valuable insights for future work on optimizing them more effectively. This study significantly contributes to advancing machine learning applications in recruitment procedures. Index Terms—Machine Learning, Quality Assurance, hiring processes, algorithm comparison, bias reduction. I. INTRODUCTION MACHINE learning is a subdivision of artificial intel ligence focused on enabling systems to learn without explicit programming. This is achieved by allowing the system to identify patterns and anticipate future actions. Machine learning is applied in various domains, including natural language processing, genetic sequence analysis, robotics, financial risk assessment, threat detection, compiler optimization, semantic web, computer security, software engineering, and image processing, as highlighted by Panesar [1] . In computing, machine learning leverages statistical methods and algorithms to help machines enhance their performance on tasks by learning from data. According to Panesar [1], the ultimate objective is to create models that can learn from examples and training data, and subsequently apply that knowledge to new scenarios. Manuscript received December 9, 2023; revised August 4, 2024 . David Santiago Bejarano Velandia is an undergraduate student of Telematics Engineering, Universidad Distrital Francisco Jos de Caldas, Bogot Colombia. (e-mail: [dsbejaranov@udistrital.edu.co](dsbejaranov@udistrital.edu.co)) Jorge Enrique Rodriguez Rodriguez is an associate professor of Telematics Engineering, Universidad Distrital Francisco Jos de Caldas, Bogota,´ Colombia. (e-mail: [jerodriguezr@udistrital.edu.co](jerodriguezr@udistrital.edu.co)). David Stevens Gonzalez Lizarazo is an undergraduate student of Telematics Engineering, Universidad Distrital Francisco Jos de Caldas, Bogota,´ Colombia. (e-mail: [dsgonzalezl@udistrital.edu.co](dsgonzalezl@udistrital.edu.co)). The software quality assurance industry has experienced substantial changes, resulting in a heightened demand for specialized professionals. The increasing complexity of modern software systems and the emphasis on their effectiveness and security has led to a greater need for QA professionals. As a result, hiring teams are facing challenges in finding candidates with the required skills and knowledge. Recruiting QA professionals has become highly competitive. According to a report by the International Association of Software Testing Professionals (ISTQB), the demand for QA professionals has surged by 30% over the p

FAQs

Which machine learning algorithms are evaluated in the study?

The study evaluates Nearest Neighbors, Linear SVM, Radial SVM, Gaussian Process, Decision Tree, Neural Network, Logistic Regression, Naive Bayes, and QDA for QA contracting procedures.

How are the algorithms evaluated?

Evaluation follows the KDD process and uses metrics such as F1-Score, recall, accuracy, and AUC-ROC, along with learning curves, boundary maps, confusion matrices, MCC, and complexity curves.

Which algorithms perform best according to the results?

Neural Network, QDA, and Gaussian Process show strong performance and thorough evaluation, making them optimal for the presented case study.

Aug 2, 2026

Upload by Levi