ANALISIS DAN KOMPARASI ALGORITMA NAÏVE BAYES DAN C4.5 UNTUK KLASIFIKASI LOYALITAS PELANGGAN MNC PLAY KOTA SEMARANG

• Main Authors: Yohana Tri Widayati, Yani Prihati, Stephanus Widjaja
• Format: Article
• Language: Indonesian
• Published: Universitas Semarang 2021-01-01
• Series: Transformatika
• Subjects: classification; customers loyalty; naïve bayes; c4.5.
• Online Access: https://journals.usm.ac.id/index.php/transformatika/article/view/2541

Customer loyalty is an important factor to the survival of a company. The problem facting today is related to the descreasing number of customer loyalty that happened to PT MNC Play. If this is allowed  to continue it is not impossible this will endanger the continuity of the company’s business. Keep in mind the factors that cause customers to have loyal and disloyal status, data mining classification techniques can be used to classify loyal and disloyal customers. Many data mining classification algorithms can be used, so it needs to be comparative to know the accuracy of each algorithm, the algorithem used is C4.5 and Naïve Bayes. The data used were 28,899MNC Play customer of Semarang City. The results of the classification  process were evaluated using cross validation, confusion matrix, ROC Curve to find the more accurate data mining classification algorithm to determine loyal and disloyal customers. Keywords: Classification, Customers Loyalty, Naïve Bayes, C4.5.