Internal Quality Audit Optimization At University Of Sumatera Utara Using K-Nearest Neighbour
DOI:
https://doi.org/10.37385/ijedr.v4i2.2982Keywords:
Audit, Higher Education, Accuracy, ClassificationAbstract
Internal quality audits play a pivotal role in ensuring the operational success of higher education institutions. Given the complexity and scale of activities within today's colleges and universities, conducting objective and activity-independent internal quality audits becomes essential. These audits aim to add value and enhance the organization's operations by adopting a systematic and disciplined approach to assess and improve risk management, control, and governance processes. In this research, we propose a novel approach to enhance the accuracy and efficiency of internal quality audits. The study focuses on processing internal quality audit data from auditors and the Quality Control Circle (QCC) of Magister of Accounting, utilizing a suitable k-nearest neighbor method. The generated system aims to provide alternative calculation processing for internal quality audit results, enabling auditors to obtain more representative outcomes. Additionally, the system facilitates better documentation practices, making it convenient for internal quality auditors to access and use the data effectively. The research findings demonstrate significant improvements, with the accuracy value reaching an impressive 75.00%, and an AUC value of 0.88 in the Excellent Classification group. These outcomes hold promising implications for the future work of internal quality auditors, empowering them to deliver more reliable and comprehensive audit results.
References
Buaton, R., Muhammad, Z., & Dilham, A. (2022). Optimization of Higher Education Internal Quality Audits Based on Artificial Intelligence. Journal of Artificial Intelligence and Engineering Applications (JAIEA), 1(2), 158-161.
Dhany, Hanna Willa. (2021). K-Nearest Neighbor Algorithm Performance in Predict Disease heart. Proceedings of SENATIKA 2021.
Eko Prasetyo. (2014), Data Mining- Managing Data Mining becomes Information use Matlab. Andi Publisher.
Gou, J., Yi. Z., Du. L. & Xiong, T. (2012). A Local Mean-Based k-Nearest Centroid Neighbor Classifier. The Computer Journal 55(6):1058-1071.
Kristin Lourensi node. (2019). Improved Accuracy. on. Method Classification Neural Networks Backpropagation Using Principal Components analysis. University of Sumatra North
Pan, Z., Wang, Y. & Ku, W. (2017). A New General Nearest Neighbor Classification Based On The Mutual Neighborhood Information. Knowledge Based Systems 121:142-152.
Rokach , L. (2008). Data mining with decision trees: Theory and applications.
Samira, A., & Nurmammad, M. (2018). Multi-disciplinary energy auditing of educational buildings in Azerbaijan: case study at a university campus. IFAC-PapersOnLine, 51(30), 311-315.
Susilo, W. (2003). Internal Quality Audit. Jakarta: Vorqista.
Toto, Puspito Andri. (2017). Determine Choice School in the Reception Participant Educate New With Use Naive Bayes and K-Nearest Neighbor Methods (Study Case: PPDB Online for Junior High School in Metro City). Journal Informatics, Volumes. 17, No.1pp.49-59.
Turban, E. et al. (2005). Decision Support and Intelligent Systems. Upper Saddle River, NJ: Prentice Hall.
Wells, SC (2009). Internal Audit at Institutions of Higher Education. Kentucky: Emerald.
Yudianto, I., Mulyani, S., Fahmi, M., & Winarningsih, S. (2021). The influence of enterprise risk management implementation and internal audit quality on universities’ performance in Indonesia. Journal of Southwest Jiaotong University, 56(2).
Zamzami, F. (2015). Internal Audit Concepts and Practices. Yogyakarta : Gadjah Mada University Press
Zhu, J., Xu, L., Liu, Y., Zhu, D., & Chen, L. (2021). The Defects and Improvements of the Internal Control Audit in Chinese Universities with respect to the Probabilistic Hesitant Fuzzy Environment. Complexity, 2021, 1-8.
