Optimalisasi K-Means Dalam Pengelompokan Ancaman Insiden Aplikasi Yang Dilaporkan Melalui Service Desk TIK

Authors

  • Rimba Prasasti Nusamandiri University image/svg+xml
  • Rifki Sadikin
  • Eni Heni Hermallani

DOI:

https://doi.org/10.24014/sitekin.v20i1.19454

Abstract

Layanan click, call, counter (3C) merupakan bentuk transformasi layanan digital Perpajakan. Insiden layanan 3C yang terjadi ini dilaporkan melalui Service Desk TIK. Banyaknya laporan insiden membuat kendala dalam penanganan penyelesaian permasalahan. Dengan menggunakan K-Means secara unsupervised learning untuk pengelompokan ancaman insiden diharapkan dapat membantu penyelesaian lebih efektif. Optimalisasi untuk meningkatkan nilai akurasi yang lebih baik dicari menggunakan word embedded dengan algortima Elkan dan algortima Lloyd padaK-Means. Hasil optimal didapatkan pada jumlah kluster 4 yang dievaluasi   menggunakan Silhouette Score, Calinski Harabasz dan Davies-Bouldin Index. Hasil optimal dari penerapan model pada algoritma K-Means dan parameter algoritma Elkan dengan word embedding CountVectorizer didapatkan sebesar 71,94% pengelompokan yang sesuai.

References

Y. I. Santoso, “Ditjen Pajak optimalisasi layanan digital, demi kejar pendapatan di tengah pandemi,” 2020. https://newssetup.kontan.co.id/news/ditjen-pajak-optimalisasi-layanan-digital-demi-kejar-pendapatan-di-tengah-pandemi (accessed Nov. 02, 2021).

K. P. Kinanti and D. Pratomo, “Pengaruh Penerapan Pendaftaran Npwp Secara Online ( E- Registration ), E-Billing Dan E-Filing Terhadap Kepatuhan Wajib ( Survei pada Wajib Pajak Orang Pribadi Non Karyawan di KPP Pratama Depok Cimanggis Tahun 2019 ),” e-Proceeding Manag., vol. 8, no. 6, pp. 1–8, 2021.

M. Zuraeva and N. Rulandari, “Analisis Kualitas Pelayanan Perpajakan dalam Rangka Meningkatkan Kepatuhan Wajib Pajak,” J. Pajak Vokasi, vol. 2, no. 1, pp. 37–44, 2020.

Direktorat Jenderal Pajak, “SURAT EDARAN DIREKTUR JENDERAL PAJAK NOMOR SE - 37/PJ/2013,” no. Agustus, 2013.

D. Safitri and S. P. Silalahi, “Pengaruh Kualitas Pelayanan Fiskus, Pemahaman Peraturan Perpajakan Dan Penerapan Sistem E-Filling Terhadap Kepatuhan Wajib Pajak: Sosialisasi Perpajakan Sebagai Pemoderasi,” J. Akunt. dan Pajak, vol. 20, no. 2, 2020, doi: 10.29040/jap.v20i2.688.

M. A. Prihandono, R. Harwahyu, and R. F. Sari, “Performance of machine learning algorithms for IT incident management,” 2020 11th Int. Conf. Aware. Sci. Technol. iCAST 2020, pp. 2–7, 2020, doi: 10.1109/iCAST51195.2020.9319487.

R. R. COSTA, Jorge, Rubén PEREIRA, “ITSM Automation - Using Machine Learning to Predict Incident Resolution Category,” no. 351, 2021.

F. Alamri and A. Widyatama, “TAM Sebagai Solusi Atas Minat Penggunaan Layanan E-Registration Wajib Pajak,” vol. 10, no. 2, pp. 89–99, 2019.

J. Luengo, D. García-Gil, S. Ramírez-Gallego, S. García, and F. Herrera, Big Data Preprocessing. 2020. doi: 10.1007/978-3-030-39105-8.

K. R. Chowdhary, Fundamentals of Artificial Intelligence. 2020. [Online]. Available: https://doi.org/10.1007/978-81-322-3972-7_19

Gong, Nan, Chunxiao Fan, Yuexin Wu, Yue Ming, “A Web Content Extraction Method Base on Punctuation Distribution and HTML Tag Similarity,” Proc. 3rd Int. Conf. Logist. Informatics Serv. Sci., 2013.

G. N. R Prasad Sr Asst professor, “Identification of Bloom’s Taxonomy level for the given Question paper using NLP Tokenization technique,” Turkish J. Comput. Math. Educ., vol. 12, no. 13, pp. 1872–1875, 2021.

D. Na and C. Xu, “Automatically generation and evaluation of stop words list for Chinese patents,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 13, no. 4, pp. 1414–1421, 2015, doi: 10.12928/TELKOMNIKA.v13i4.2389.

A. Jabbar, S. Iqbal, M. I. Tamimy, S. Hussain, and A. Akhunzada, “Empirical evaluation and study of text stemming algorithms,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5559–5588, 2020, doi: 10.1007/s10462-020-09828-3.

K. K. Purnamasari and I. S. Suwardi, “Rule-based Part of Speech Tagger for Indonesian Language,” IOP Conf. Ser. Mater. Sci. Eng., vol. 407, no. 1, 2018, doi: 10.1088/1757-899X/407/1/012151.

W. bin, angela wang, fenxiao chen, yuncheng wang and c.-c. jay kuo, “Evaluating word embedding models : methods and experimental results,” vol. 8, 2019, doi: 10.1017/ATSIP.2019.12.

M. Hamisu and A. Mansour, “Detecting Advance Fee Fraud Using NLP Bag of Word Model,” pp. 94–97, 2020.

A. Addiga and S. Bagui, “Sentiment Analysis on Twitter Data Using Term Frequency-Inverse Document Frequency,” pp. 117–128, 2022, doi: 10.4236/jcc.2022.108008.

D. K. Hashim and L. A. N. Muhammed, “Performance of K-means algorithm based an ensemble learning,” Bull. Electr. Eng. Informatics, vol. 11, no. 1, pp. 575–580, 2022, doi: 10.11591/eei.v11i1.3550.

K. Aoyama, K. Saito, and T. Ikeda, “Accelerating a Lloyd-Type k-Means Clustering Algorithm with Summable Lower Bounds in a Lower-Dimensional Space,” no. 11, pp. 2773–2783, 2018.

C. Elkan, “Using the Triangle Inequality to Accelerate k-Means,” Proceedings, Twent. Int. Conf. Mach. Learn., vol. 1, pp. 147–153, 2003.

K. R. Shahapure and C. Nicholas, “Cluster Quality Analysis Using Silhouette Score,” pp. 2020–2021, 2020, doi: 10.1109/DSAA49011.2020.00096.

A. K. Singh, S. Mittal, P. Malhotra, and Y. V. Srivastava, “Clustering Evaluation by Davies-Bouldin Index(DBI) in Cereal data using K-Means,” Proc. 4th Int. Conf. Comput. Methodol. Commun. ICCMC 2020, no. Iccmc, pp. 306–310, 2020, doi: 10.1109/ICCMC48092.2020.ICCMC-00057.

X. Wang and Y. Xu, “An improved index for clustering validation based on Silhouette index and Calinski-Harabasz index,” IOP Conf. Ser. Mater. Sci. Eng., vol. 569, no. 5, 2019, doi: 10.1088/1757-899X/569/5/052024.

Downloads

Published

2022-11-30

Issue

Vol. 20 No. 1 (2022): Desember 2022

Section

Articles

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License

 

Copyright Notice

An author who publishes in the SITEKIN Journal agrees to the following terms:

  • Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
  • Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
  • Author is  permitted and encouraged to post his/her  work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).

Read more about the Creative Commons Attribution-ShareAlike 4.0 Licence here: https://creativecommons.org/licenses/by-sa/4.0/.