Data Mining for Quality Prediction in Software-as-A-Service Concept

Methodology/Approach: To develop the quality prediction model, this study utilized a data mining methodology to extract knowledge from historical data collected from the offset printing industry, focusing on manufacturing parameters. Four classification algorithms (Decision Tree, k-NN, Naive Bayes, Random Tree) were employed and compared to identify the most precise model specifically tailored for offset printing. Subsequently, the prediction model was integrated into a web-based system to enable quality prediction.


Findings: This study demonstrates practicality of integrating quality prediction into the SaaS framework, specifically for offset printing. This integration is designed to predict how manufacturing control parameters, such as printing slope angle, engine temperature, paper size, ink density, and roller speed, relate to the occurrence of product defects such as crumpled paper and imprecise printing.


Research Limitation/implication: Generalizability is constrained by its focus on the offset printing industry, and prediction accuracy relies on historical data, which can vary across manufacturing sectors, affecting model performance.


Originality/Value of paper: This article presents the concept and practical implementation of utilizing data mining in a SaaS environment to enhance the quality of manufacturing, with a particular emphasis on the offset printing sector.