Analisis Dan Prediksi Perilaku Pengguna Website Menggunakan Algoritma Deep Learning Berbasis Web Usage Mining
Article Sidebar
Main Article Content
Abstract
Article Summary
The rapid growth of web technology has led to a significant increase in user interaction data, which can be utilized to better understand user behavior patterns. This study aims to analyze and predict website user behavior using a Deep Learning approach based on Web Usage Mining. The methodology consists of several stages, including user activity log data collection, data preprocessing, pattern extraction, and predictive model development using Deep Learning algorithms. The dataset used in this study includes historical user interaction data such as clicks, session duration, and page navigation paths. The results indicate that the Deep Learning approach is capable of identifying user behavior patterns more accurately compared to conventional methods, while also providing more adaptive predictions in response to dynamic user behavior changes. Furthermore, the developed model can be effectively applied to support recommendation systems and enhance user experience on websites. In conclusion, the integration of Web Usage Mining and Deep Learning proves to be an effective approach for improving the analysis and prediction of website user behavior, contributing significantly to the advancement of artificial intelligence applications in web-based systems.
Keywords
Article Keywords
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Agustini, P., Iqbal, M., Akbar, V. A., & Kurniawan, R. (2025). Perbandingan algoritma deep learning untuk analisis sentimen ekowisata di Bogor: Comparison of deep learning algorithm in sentiment analysis ecotourism in Bogor. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(3), 1133–1142. https://doi.org/10.57152/malcom.v5i3.2191
Ahyuna, A., Metoli, M., Manduli, P., & Syam, A. (2025). Perancangan sistem informasi penjualan berbasis web dengan penerapan algoritma Light Gradient Boosting Machine (LightGBM) untuk prediksi pola pembelian konsumen. DIPAKOMSI, 18(1), 21–25. https://doi.org/10.36774/dipakomsi.v18i1.1772
Anggraeni, S. R. (2025). Integrasi data analytics dalam kajian perilaku pengguna untuk pengembangan layanan informasi. Modem: Jurnal Informatika dan Sains Teknologi, 3(2), 1–12. https://doi.org/10.62951/modem.v3i2.364
Arifandy, M., & Sunaringtyas, S. U. (2021). Rancang bangun model machine learning untuk mendeteksi malicious webpage dengan metode Wang et al. (2017). Info Kripto, 15(2), 63–68. https://doi.org/10.56706/ik.v15i2.3
Firmansyah, M. D., Christopher, C., & Siahaan, M. (2026). Analisis keamanan sistem informasi menggunakan algoritma Support Vector Machine terhadap pengguna Shopee. TEKNIMEDIA: Teknologi Informasi dan Multimedia, 7(1), 154–160. https://doi.org/10.46764/teknimedia.v7i1.344
Harwati, H., Rosidah, L. A., & Milya, R. R. (2025). Penerapan deep learning untuk analisis sentimen ulasan produk dalam memprediksi perubahan permintaan pasar pada platform e-commerce. Journal of Science, Technology, and Innovation, 1(2), 72–80. https://doi.org/10.65310/v7bm9213
Mayasari, N., Rizal, C., & Wulandari, F. (2024). Penerapan metode klasifikasi karakteristik kepribadian berbasis website. Journal Zetroem, 6(2), 27–30. https://doi.org/10.36526/ztr.v6i2.3755
Rafidah, A. O., Azzahra, K. A., Banowati, T. A., Sari, W. K., Tania, K. D., & Fathoni, F. (2026). Analisis perbandingan Random Forest dan Support Vector Machine dalam klasifikasi tingkat risiko kecanduan judi online berbasis K-Means clustering pada pola transaksi pengguna. JATI (Jurnal Mahasiswa Teknik Informatika), 10(3), 4142–4148. https://doi.org/10.36040/jati.v10i3.18168
Rani, S., Aslamiah, R., Amrullah, A., & MT, M. (2025). Sistem klasifikasi konten radikal website dakwah menggunakan algoritma KNN. Technologia: Jurnal Ilmiah, 16(3), 604–612. https://doi.org/10.31602/tji.v16i3.19701
Rudianto, S., Solihati, T. I., & Kania, R. (2025). Data mining untuk analisis perilaku dan kecerdasan bisnis. PT Literapedia Utama Publishing.
Sitio, A. S., & Sianturi, F. A. (2024). Penerapan algoritma machine learning dalam analisis pola perilaku penggunaan internet. Dike, 2(2), 46–51. https://doi.org/10.69688/dike.v2i2.102
Tukino, T. (2025). Penerapan algoritma Convolutional Neural Network untuk klasifikasi sentimen pada layanan e-commerce. Jurnal Desain dan Analisis Teknologi, 4(1), 44–53. https://doi.org/10.58520/jddat.v4i1.72
Tyas, F. A., Basir, A., & Ardhin, A. E. (2026). Prediksi risiko penggunaan media sosial terhadap kesehatan mental menggunakan exploratory data analysis (EDA) dan Cross Industry Standard Process for Data Mining (CRISP-DM). Jurnal Teknologi Informasi dan Ilmu Komputer, 13(2), 487–498. https://doi.org/10.25126/jtiik.2026133
Yessy Asri, S. T., Kuswardani, D., & Kom, M. (2024). Machine learning & deep learning: Analisis sentimen menggunakan ulasan pengguna aplikasi. Uwais Inspirasi Indonesia.
Yuliana, S., Kom, M., Nurcahyo, A. C., Kom, S., Kom, M., Paradise, S., & Kristianto, E. A. H. (2025). Machine learning algorithms and their use cases. Penerbit Widina.
Zhafir, M., & Rukhiviyanti, N. (2026). Analisis perbandingan algoritma machine learning untuk prediksi konversi penjualan UMKM Shiroapparel pada platform social commerce di TikTok Shop. TeIKa, 16(1), 71–79. https://doi.org/10.36342/5dbmw962