Arif, Mhd. Fakhrozi
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Determining Customer Satisfaction Level to Determine Batik Business Development Using Naive Bayes Algorithm Arif, Mhd. Fakhrozi; Hasugian, Abdul Halim
Sistemasi: Jurnal Sistem Informasi Vol 13, No 4 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i4.4283

Abstract

Batik is one of the cultural heritages that must be preserved and developed. every business actor must experience very tight competition conditions, namely in the batik clothing business. Customer satisfaction is a very important aspect to pay attention to in order to increase business profits. The purpose of this research is to make it easier for Batik Berjaya Labuhanbatu Utara to find out what are the factors that affect customer satisfaction for the future development of Batik Berjaya Labuhanbatu Utara's business, and to find out the rediction results by looking at the accuracy of Naïve Bayes so that Batik Berjaya Labuhanbatu Utara can meet customer satisfaction. This research uses the Naive Bayes Algorithm Method whose results can later facilitate batik business managers in making decisions and improving the quality of products and services provided to customers. By calculating the classification results using the Naive Bayes algorithm with a total of 132 data, as a manual calculation, 30 data are used, namely, 80% of the training data totaling 24, 20% of the test data totaling 6 obtained accuracy 83.33%, precision 100%, recall 75%, specifity 100% and f1-score 85.71. Using the Naive Bayes algorithm helps classification, data in the form of attributes and labels are held training data and test data, where training data labeling must be determined at the beginning in the form of categorical information, namely satisfied and dissatisfied, then predictions are made based on the highest data to get satisfied and dissatisfied labels from test data.