Implementation of artificial neural network using scaled conjugate gradient in ISO 9001:2015 audit findings classification

Abstract

Auditors of Quality Management System (QMS) face challenges in generating accurate audit reports due to some factors that can be attributed to technical competence, experience, time, auditee reaction, and other factors. Incorrect clauses cited in audit reports may result to loss of integrity of the auditor and the auditing procedure itself, hence, it is important that auditors should be careful in citing clauses of the standard to avoid chaos and complaints from auditees. To resolve this issue, this paper presents the implementation of Artificial Neural Network (ANN) using Scaled Conjugate Gradient (SCG) algorithm to classify audit findings based on the clauses of the ISO 9001:2015 QMS Requirements international standard. In this paper, the author explored how the neural network can predict the correct clause of the standard according to text patterns of audit findings. Based on modelling results, the neural network has generated a Cross Entropy (CE) values of 6.39, 18.09, 18.09 and Percentage Error (PE) values of 21.83, 21.58, and 22.39 in training, testing, and validation environments, respectively. Moreover, the model has achieved a combined Classification Accuracy (CA) of 96%, as for which, based on the actual implementation, the model has accurately predicted 95% of the audit findings analyzed.