Claim Missing Document
Check
Articles

Found 2 Documents
Search

The Influence of Social Media, Price, and Venue on Concert Ticket Purchasing Decisions at The Motikdong.Com Website Wahyudi Wahyudi
INTERACTION: Jurnal Pendidikan Bahasa Vol 10 No 1 (2023): INTERACTION: Jurnal Pendidikan Bahasa
Publisher : Universitas Pendidikan Muhammadiyah (UNIMUDA) Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36232/jurnalpendidikanbahasa.v10i1.4423

Abstract

This study examines whether social media, price, and venue influence the Decision to Purchase Concert Tickets. This research is quantitative. The sample in this study is concert audience customers who have purchased concert tickets on the Motikdong.com website. The population in this study were Motikdong Indonesia Instagram account followers and ticket buyers who had bought directly on the motikdong.com website. The sample in this study was 335 respondents who were determined using the Slovin formula. The results of data analysis using SPSS 23 prove that there is a positive and significant influence both partially and simultaneously between Social media, price, and Venue variables on Purchase Decisions on concert tickets on the motikdong.com website with a contribution (R2) of 77.2% and a value F count, which is 373,982 > F table, which is 2,631, which means that social media, price, and venue variables influence the decision to purchase tickets on the motikdong.com website. Partially, each independent variable significantly influences the dependent variable, where the venue variable has a dominant value compared to other independent variables, with a value of 93.4.
Penerapan Algoritma Machine Learning Untuk Deteksi Akses Tidak Sah Pada SIAKAD IAI Al-Ghurabaa Wahyudi Wahyudi; Mohammad Noviansyah; Hafdiarsya Saiyar; Martua Hami Siregar; Desmulyati Desmulyati
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 6 (2025): Desember 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i6.10021

Abstract

Abstrak: Sistem Informasi Akademik (SIAKAD) merupakan komponen vital dalam pengelolaan data akademik di perguruan tinggi, termasuk Institut Agama Islam Al-Ghurabaa. Akses tidak sah terhadap sistem ini dapat menyebabkan kebocoran data, perubahan nilai, dan gangguan integritas informasi akademik. Penelitian ini bertujuan untuk mengembangkan model deteksi dini terhadap aktivitas akses tidak sah menggunakan algoritma machine learning.Metode penelitian meliputi pengumpulan dan pra-pemrosesan data log akses SIAKAD, ekstraksi fitur perilaku pengguna (frekuensi login, waktu akses, IP address, dan pola aktivitas), serta pelatihan model klasifikasi menggunakan algoritma Random Forest dan Support Vector Machine (SVM). Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score.Hasil pengujian menunjukkan bahwa algoritma Random Forest menghasilkan tingkat akurasi tertinggi sebesar 97,3%, dengan kemampuan deteksi anomali akses yang lebih baik dibanding SVM (93,8%). Model yang diusulkan mampu mendeteksi aktivitas login mencurigakan secara real-time, sehingga dapat menjadi lapisan keamanan tambahan untuk SIAKAD IAI Al-Ghurabaa. Penerapan machine learning dalam keamanan aplikasi akademik terbukti efektif dalam meningkatkan ketahanan sistem terhadap serangan berbasis autentikasi dan penyalahgunaan akun penggunaKata kunci: SIAKAD; keamanan data; deteksi anomali; machine learning; Random Forest; SVM; Abstract: The Academic Information System (SIAKAD) is a vital component of academic data management in higher education institutions, including Institut Agama Islam Al-Ghurabaa. Unauthorized access to this system can lead to data breaches, grade manipulation, and loss of information integrity. This research aims to develop an early detection model for unauthorized access using machine learning algorithms. The methodology includes collecting and preprocessing SIAKAD access log data, extracting behavioral features (login frequency, access time, IP address, and activity patterns), and training classification models using Random Forest and Support Vector Machine (SVM) algorithms. Evaluation metrics used are accuracy, precision, recall, and F1-score. Experimental results show that the Random Forest algorithm achieved the highest accuracy of 97.3%, outperforming SVM (93.8%) in detecting anomalous access attempts. The proposed model can identify suspicious login activities in real-time, providing an additional security layer for SIAKAD IAI Al-Ghurabaa. The study demonstrates that machine learning-based intrusion detection is effective in enhancing system resilience against authentication-based attacks and user account misuse.Keywords: SIAKAD; data security; anomaly detection; machine learning; Random Forest; SVM;