Abstrak
Perkembangan teknologi semakin memudahkan kegiatan manusia dan hampir semua kalangan memiliki ponsel. Sehingga ponsel menjadi alat yang penting dalam berkomunikasi bagi kebanyakan orang terutama SMS. Banyaknya pesan yang masuk bisa tidak memungkinkan untuk mengklasifikasikan SMS spam secara manual. Untuk itu dilakukan pengklasifikasian SMS spam menggunakan teknik klasifikasi dalam data mining. Banyaknya algoritma yang tersedia memungkinkan kita untuk menggunakan salah satunya sebagai algoritma terbaik untuk klasifikasi SMS spam. Untuk itu dilakukan pengujian beberapa algoritma klasifikasi dengan dataset SMS yaitu algoritma Naïve Bayes, Decision Tree dan SVM. Dari hasil Analisa pengujian didapatkan bahwa algoritma Naïve Bayes memiliki kemampuan yang lebih baik dibandingkan algoritma SVM dan Decision Tree. Karena nilai recall algoritma Naïve Bayes sebesar 0.93 pada kelas SMS fraud dan 0.92 pada kelas SMS promo, sedangkan f1-score algoritma Naïve Bayes lebih tinggi dibanding algoritma lainnya dan nilai accuracy Naïve Bayes sebesar 0.94.
The high public interest in transactions using credit cards in the banking sector has the potential for higher credit card fraud. This study uses a credit card fraud dataset that consisting of 284,807 data obtained from Kaggle. The dataset in this study is class-imbalanced data with a comparison between the major class of 99.8% and the minor class of 0.2%. This class-imbalanced data problem will be solved by applying undersampling. In order to determine the performance of the classification algorithm that is most suitable for solving class-imbalanced data problems, a comparison of the Naïve Bayes, k-Nearest Neighbor (kNN) and Neural Network algorithms will be carried out. The t-test in this study was conducted to determine the significance of differences between algorithms. Algorithm performance evaluation uses accuracy and AUC (area under the curve) values. The test results in this study is Neural Network has better performance than other algorithms because it has the highest accuracy value of 93.59% and AUC value of 0.977. Based on the t-test results, the Neural Network with k-NN has a significant difference, in contrast to the Neural Network with Naïve Bayes there is no significant difference.
Since the pandemic, various sectors have shifted their online activities, which have also been applied to education, specifically in universities. Universities have individuals with different conditions, which encourages the management to provide information systems that support the implementation of activities at these universities. Not only learning activities but also academic administration is generally known as the Academic Information System (AIS). AIS was implemented at the Health Polytechnic Ministry of Health in Surabaya, labelled Academic Management Information System (SIM Akademik). This polytechnic has campuses spread across several cities in East Java. Each campus has different resources, thus supporting the digital divide. This study’s objective was to determine the effect of the digital divide, user satisfaction, and individual performance of Academic SIM users. These examine could develop the theory of the three variables and determine the digital range between campuses and user satisfaction. According to the results of three hypotheses tested using PLS-SEM with the Disjoint Two-Step Approach method, the digital divide had a significant positive effect on user satisfaction, the same as user satisfaction on individual performance. The digital divide had a positive, however not statistically significant, impact on individual performance. Furthermore, there was a digital divide between campuses in two aspects of measurement, and academic SIM user satisfaction is greater than 85% in all aspects of size. Employees experience the most significant performance improvement when using Academic SIMs, followed by students at 85,76 % and lecturers at 79,44 %.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.