Article Per Year (5 Year)
p-Index From 2021 - 2026
2.409
P-Index
This Author published in this journals
All Journal Jurnal Mantik Penusa SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan JIPN (Journal of Informatics Pelita Nusantara) The IJICS (International Journal of Informatics and Computer Science) Jurnal Sains dan Teknologi TRIDARMA: Pengabdian Kepada Masyarakat (PkM) Jurnal Teknik Informatika C.I.T. Medicom INFOKUM Journal of Computer Networks, Architecture and High Performance Computing Jurnal Pengabdian kepada Masyarakat Nusantara Jurnal Sistem Informasi dan Teknologi Jaringan Jurnal Media Informatika Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan (JUSTIKPEN) Jurnal Armada Informatika Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Jurnal Kolaborasi Sains dan Ilmu Terapan Jurnal Sistem Informasi dan Teknologi Jaringan Jurnal Pengabdian Kepada Masyarakat Teknologi Informasi dan Komunikasi
R. Mahdalena Simanjorang
Dosen Teknik Informatika, STMIK Pelita Nusantara, Medan
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Physics Public Health Social Sciences Other

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Implementasi Big Data Analytics Untuk Deteksi Pola Penyalahgunaan Bantuan Sosial Menggunakan Metode Clustering R Mahdalena Simanjorang; Agustina Simangunsong; Dini Auliah; Rabbiatul Adawiyah
Jurnal Kolaborasi Sains dan Ilmu Terapan Vol. 5 No. 1 (2026): Edisi Juli - Agustus In Press
Publisher : Utiliti Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69688/juksit.v5i1.149

Abstract

Kajian ini bertujuan untuk menerapkan pendekatan Big Data Analytics guna mengidentifikasi pola penyimpangan dalam penyaluran bantuan sosial dengan memanfaatkan algoritma K-Means Clustering terhadap 10.000 data penerima dari Data Terpadu Kesejahteraan Sosial (DTKS). Proses analisis dilakukan melalui kerangka Knowledge Discovery in Databases (KDD) yang mencakup tahapan kurasi data, pembersihan data, transformasi data, pengelompokan, serta evaluasi hasil menggunakan bantuan perangkat Python dan RapidMiner. Temuan penelitian menunjukkan bahwa algoritma K-Means Clustering mampu mempartisi penerima bantuan ke dalam tiga kelompok berbeda. Kelompok pertama yang terdiri dari 4.570 data (45,7%) merupakan penerima yang sah dengan ciri pendapatan terbatas dan kepemilikan aset rendah. Kelompok kedua mencakup 3.200 data (32%) yang berpotensi mengalami kesalahan data dengan kondisi ekonomi menengah. Sementara itu, kelompok ketiga sebanyak 2.060 data (20,6%) terdeteksi sebagai kelompok dengan indikasi penyalahgunaan, yang dicirikan oleh pendapatan rata-rata mencapai Rp6.500.000 serta kepemilikan aset yang tinggi. Proses validasi dengan Silhouette Score memperoleh nilai 0,68, sementara Davies-Bouldin Index menghasilkan angka 0,62, yang keduanya menandakan bahwa struktur cluster yang terbentuk tergolong memadai. Penelitian ini memberikan sumbangsih bagi pengembangan Big Data Analytics dalam sistem pengambilan keputusan di sektor kesejahteraan sosial, terutama dalam upaya mendeteksi potensi penyalahgunaan program bantuan.
Application of the K-Means Clustering Algorithm for Sales Data Clustering to Identify Best-Selling Products at PT Cahaya Surga Teknik Indonesia Amran Sitohang; R. Mahdalena Simanjorang; Fittra Ferdiansyah; Angel Nurfadilah
Jurnal Armada Informatika Vol 10 No 1 (2026): Juni
Publisher : STMIK Methodist Binjai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36520/jai.v10i1.315

Abstract

Business competition demands that companies utilize sales data as a basis for strategic decision-making. PT Cahaya Surga Teknik Indonesia has sales data that continues to grow each period, but has not been optimally utilized to identify best-selling products. This study aims to apply the K-Means Clustering algorithm to group sales data so that it can identify the categories of best-selling products, medium-selling products, and less-selling products. The research method uses data mining with KDD (Knowledge Discovery in Database) stages including data selection, preprocessing, transformation, clustering process using the K-Means algorithm, and evaluation of cluster results. The research dataset consists of annual sales data (content year) with attributes of number of transactions, number of sales, and total revenue. The results show that the K-Means algorithm is able to divide the data into 3 main clusters: the very best-selling product cluster, the moderately best-selling product cluster, and the less-selling product cluster. The clustering results can help companies in determining stock strategies, promotions, and sales planning.
Enhancing Product Recommendations Using ALS Matrix Factorization on Retailrocket with Apache Spark Agustina; R. Mahdalena Simanjorang; Bagas Multasyah; Bagus Rivaldi
The IJICS (International Journal of Informatics and Computer Science) Vol. 10 No. 2 (2026): July
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/ijics.v10i2.9845

Abstract

The rapid growth of e-commerce has generated massive volumes of user interaction data, requiring recommendation systems capable of providing accurate and relevant product suggestions. However, conventional recommendation systems still face sparsity issues and low prediction accuracy in large-scale data environments. This study aims to improve the accuracy of big data-based product recommendation systems by implementing Matrix Factorization using the Alternating Least Squares (ALS) algorithm. The research utilized the Retailrocket E-commerce Dataset consisting of 104,287 interaction records, 18,642 users, and 7,831 products with a sparsity level of 96.8%. Implicit interactions, including product views, add-to-cart activities, and purchases, were transformed into weighted preference values to represent user behavior. The model was implemented using Apache Spark MLlib within a distributed computing environment. Model evaluation was conducted using RMSE, MAE, Precision@10, and Recall@10 metrics with a 5-fold cross-validation approach. The experimental results indicate that the optimal configuration was achieved using 50 latent factors, 0.05 regularization, and 20 iterations, producing an RMSE value of 0.836, MAE of 0.689, Precision@10 of 0.861, and Recall@10 of 0.824. These findings demonstrate that ALS-based Matrix Factorization effectively improves recommendation quality while supporting scalability for large-scale data processing in modern e-commerce environments. Keywords: Matrix Factorization, Alternating Least Squares, Recommendation System, Big Data, Collaborative Filtering.
LSTM-Based Deep Learning Approach for Hoax Detection on Indonesian Social Media Nuraisana nuraisana; R. Mahdalena Simanjorang; Thania Rizky Ristanti; Della Triyani
The IJICS (International Journal of Informatics and Computer Science) Vol. 10 No. 2 (2026): July
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/ijics.v10i2.9899

Abstract

The widespread adoption of social media, particularly Facebook, has drastically accelerated information dissemination while simultaneously amplifying the spread of misinformation. Hoax content poses a serious threat to public trust and social cohesion. This study proposes a hoax classification system based on the Long Short-Term Memory (LSTM) architecture, selected for its inherent ability to model sequential dependencies in textual data. The experimental workflow covered text preprocessing (case folding, tokenization, stopword removal, and stemming), word vectorization using the Keras Tokenizer, and end-to-end LSTM model training on the “Indonesian Fact and Hoax Political News” dataset from Kaggle, totaling 4,502 samples with a balanced 80:20 train-test split. Experimental results demonstrate the proposed model achieves 92.44% accuracy, 92.63% precision, 92.22% recall, and a 92.42% F1-score on the test set. These findings confirm that LSTM effectively captures contextual and sequential linguistic patterns in Indonesian-language content, offering a viable and scalable solution for automated hoax detection on social media platforms.
Sistem Pendukung Keputusan Pemilihan Guru Berprestasi Dengan Metode TOPSIS R. Mahdalena Simanjorang; Agustina Simangunsong; Amran Sitohang; Josua Lumban Tobing; Sartika Simanjorang
Jurnal Media Informatika Vol. 7 No. 1 (2026): Edisi Januari - Februari
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v7i1.8352

Abstract

Pemilihan guru berprestasi merupakan aspek strategis dalam peningkatan mutu pendidikan karena berfungsi sebagai sarana evaluasi dan motivasi bagi tenaga pendidik. Namun, proses penilaian yang masih dipengaruhi subjektivitas dapat menimbulkan keputusan yang kurang maksimal. Penelitian ini diarahkan dalam hal perancangan serta pembangunan SPK  yang diimplementasikan dalam platform menggunakan web dalam pemilihan guru berprestasi dengan mengaplikasikan metode TOPSIS. Teknik tersebut dilakukan pemilihannya karena memiliki kemampuan untuk menghasilkan evaluasi alternatif secara tertata dengan memperhatikan tingkat derajat kesesuaian relatif dengan solusi ideal positif maupun solusi negatif yang ideal. Tahapan awal penelitian dilaksanakan melalui kegiatan analisis kebutuhan sistem berdasarkan temuan dari wawancara serta studi literatur untuk menetapkan kriteria penilaian, meliputi kinerja, inovasi pembelajaran, kedisiplinan, dan prestasi akademik. Pengembangan sistem dilakukan menggunakan model waterfall, mencakup perancangan basis data, antarmuka pengguna, serta implementasi perhitungan TOPSIS. Hasil evaluasi yang diperoleh dari pengujian mengindikasikan bahwa alternatif AC menunjukkan perolehan nilai preferensi paling tinggi sebesar 0,677, diikuti oleh AE (0,647), AA (0,457), AB (0,438), dan AD (0,286). Berdasarkan hasil tersebut, alternatif A3 ditetapkan sebagai guru berprestasi terbaik. Sistem yang dikembangkan mampu mendukung proses penentuan keputusan dapat dilakukan secara lebih sistematis, transparan, serta berbasis kriteria yang terukur, efisien
Co-Authors Agustina Amalia Rossa Amran Sitohang Angel Nurfadilah Bagas Multasyah Bagus Rivaldi Bosker Sinaga Della Triyani Desi Endiyana Br.Purba Dini Auliah Eko Sutanto Erlifta Cresensia Erwin Panggabean Fitri Amalia Fittra Ferdiansyah Hartati Palentina Sipahutar Hasanul Fahmi Hasugian, Penda Sudarto Hengki Tamando Sihotang Hutahaean, Harvei Desmon Jeremia Sembiring Jijon Raphita Sagala Josua Lumban Tobing Karianus Zai M. Rifan Afandi Muhammad Ridho Syahwana Nelvan Saleks Oktorianus Tafonao Nuraisana Nuraisana Petti Indrayati Sijabat Pria Dimas Putri Khairunnisa Rabbiatul Adawiyah Rizki Amarullah Sartika Simanjorang Simangunsong, Agustina Sinaga, Anita Sindar R M Tengku Muhammad Rizal Thania Rizky Ristanti Yuda Perwira