Claim Missing Document
Check
Articles

Actor-Critic Reinforcement Learning for Personalized STEM Learning Path Optimization Hatta, Muhammad; Magdalena, Lena; Putra, Dwi Pasha Anggara; Runa, Yohanes Michael Fouk; Irfansyah, Ananda; Valentino, Fernando
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1270

Abstract

This study addresses the critical need for adaptive learning in non-formal education settings, particularly Community Learning Centres (PKBM) in Indonesia, where student heterogeneity and limited resources challenge conventional teaching methods. We developed a personalized learning path optimization model using Actor-Critic Reinforcement Learning (RL) to enhance STEM competency development. The novel framework integrates cognitive, affective, and personality features to dynamically adjust material difficulty based on real-time analysis of student cognitive states (quiz performance, completion rate) and affective conditions (emotional level), moving beyond static predictive approaches. Experimental results on a synthetic dataset demonstrate that the Actor-Critic agent achieves statistically significant higher rewards (-2.92 vs -3.01, p<0.05) and greater output stability compared to a random baseline. Although the absolute reward difference is modest, it reflects more consistent adaptive policy performance, despite limited effect size (Cohen's d=0.0317). Feature importance analysis confirms that quiz_score and emotion_level are the dominant factors influencing adaptive recommendations, while personality traits show negligible impact. The framework offers a viable pathway for scalable, personalized learning in resource-constrained environments. Future work should validate the model with real-world student data and refine reward functions to strengthen practical impact.
Implementation of the COBIT 2019 Framework on Information Technology Governance and Risk Management (Study Case: CV. Syntax Corporation Indonesia) Solikhah, Mar'atus; Magdalena, Lena; Hatta, Muhammad
Eduvest - Journal of Universal Studies Vol. 4 No. 6 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i7.1504

Abstract

CV. Syntax Corporation Indonesia is one of the companies that has adopted the application of information technology. In the process of its implementation, CV. Syntax Corporation Indonesia has not yet had an assessment that became an evaluation process of the management or application of information technology in it. Therefore, an assessment process is needed on the governance and management of the information technology it adopts. To support the assessment process, it is assisted by a framework that can be used as a tool during the assessment process, namely using COBIT 2019. The research method used is a qualitative-descriptive method that can describe an event that is happening now through measurement. APO12 and BAI09 sub-domains were obtained based on the mapping results. From the mapping results on the RACI chart and capability level, APO12 is at level 3. As for BAI09, it is at level 2. From the mapping process to the strategic objectives of CV. Syntax Corporation Indonesia has a main focus, namely governance on services and a focus on risk management. This result will form a Critical Success Factor (CSF) which will be a direction in providing recommendations as advice given. On the other hand, there is also a website in the form of a dashboard which is a tool to visualize the results of this assessment process.
Analysis of Customer Satisfaction with the Application of Data Mining Using the K-Means Clustering Method in CV. Green Publisher Indonesia Syawaludin, Dwi Febri; Hatta, Muhammad; Kusnadi, Kusnadi
Eduvest - Journal of Universal Studies Vol. 5 No. 1 (2025): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i1.1708

Abstract

In this digital era, data has become one of the most valuable assets for all companies. Data mining is a method that can be used to explore knowledge. The current research aims to analyze CV customer satisfaction. Green Publisher Indonesia by applying data mining techniques using the k-means clustering method. In this research, data will be collected regarding customer preferences and levels of satisfaction through sources such as online surveys. The data will be analyzed into the rapidminer 5.3 system using the k-means clustering algorithm. The research material used is customer data that has been obtained within a certain period by providing an Online Questionnaire (Google Form). In this research, researchers used one of the methods in Data Mining, namely the K-Means Clustering method. The results of the clustering execution using K-Means Clustering were 163 data resulting in 2 clusters with details of cluster 0 as 131 data or 80.36% and cluster 1 as 32 data or 19.64%.  The results of the analysis show that there is a significant difference in the level of satisfaction between the two clusters.
Implementasi Sistem Prediksi Pendapatan Penjualan Susu Kemasan Menggunakan Metode Regresi Linier Berganda Renaldi, Refan; Magdalena, Lena; Hatta, Muhammad
JSR : Jaringan Sistem Informasi Robotik Vol 9, No 2 (2025): JSR:Jaringan Sistem Informasi Robotik
Publisher : AMIK Mitra Gama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58486/jsr.v9i2.555

Abstract

Industri susu kemasan di Indonesia mengalami perkembangan signifikan seiring meningkatnya kesadaran masyarakat akan pentingnya asupan nutrisi. CV Cita Nasional sebagai produsen susu kemasan menghadapi tantangan dalam memprediksi penjualan secara akurat di wilayah Jawa Barat. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem prediksi penjualan menggunakan metode Regresi Linier Berganda berbasis web. Data penjualan selama 24 bulan (Januari 2023 - Desember 2024) dari enam wilayah distribusi dianalisis dengan variabel independen meliputi Cup, Pp, Mp, Ygt, Y Btl, Spm-c-s, Ppm serta transformasi musiman Month_Sin dan Month_Cos. Implementasi sistem menggunakan framework Laravel untuk backend dan frontend, serta Python untuk pemodelan. Hasil evaluasi model menunjukkan MAE sebesar 0,0250, MSE 0,0011, RMSE 0,0334, dan MAPE 11,71% pada data testing, yang mengindikasikan akurasi prediksi yang baik. Sistem berhasil mengidentifikasi variabel Spm-c-s sebagai faktor terkuat dengan korelasi 0,9542 terhadap pendapatan. Penelitian ini memberikan kontribusi dalam bentuk sistem prediksi yang dapat membantu optimalisasi perencanaan produksi dan distribusi.
ANALISIS SENTIMEN APLIKASI PADI UMKM DENGAN PENINGKATAN KINERJA ALGORITMA KNN Febima, Mesi; Solihin, Unang; Magdalena, Lena; Hatta, Muhammad; Asfi, Marsani; Christina, Stefanny
Jurnal Digit : Digital of Information Technology Vol 15, No 2 (2025)
Publisher : Universitas Catur Insan Cendekia (CIC) Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51920/jd.v15i2.446

Abstract

Dalam era digital, Usaha Mikro, Kecil, dan Menengah (UMKM) dituntut untuk memanfaatkan teknologi guna memperluas pasar dan meningkatkan daya saing. Salah satu inovasi yang mendukung hal tersebut adalah aplikasi PaDi UMKM, platform hasil inisiatif Kementerian BUMN yang mempertemukan BUMN dengan produk-produk berkualitas dari UMKM di seluruh Indonesia. Keberhasilan aplikasi ini tidak hanya ditentukan oleh fungsionalitasnya, tetapi juga oleh persepsi dan pengalaman pengguna yang tercermin melalui ulasan di Google Playstore. Untuk memahami persepsi tersebut, dilakukan analisis sentimen menggunakan pendekatan Natural Language Processing (NLP) dan pembelajaran mesin. Penelitian ini bertujuan untuk menganalisis sentimen positif dan negatif terhadap aplikasi PaDi UMKM dengan membandingkan performa algoritma K-Nearest Neighbor (KNN) dan Improved K-Nearest Neighbor (IKNN). Proses penelitian meliputi pengumpulan data ulasan, praproses teks, pembagian data latih dan uji, penerapan algoritma, serta evaluasi hasil klasifikasi menggunakan confusion matrix. Berdasarkan hasil confusion matrix, nilai K = 5 memberikan performa terbaik dibandingkan K = 3, K = 7, dan K = 9, dilihat dari peningkatan nilai Precision 50 % positif dan 67% negatif, Recall 80% positif dan 33% negatif, F1-Score 62% positif dan 44% neagtif, dan Accuracy 10% positif dan 12 negatif. Sebaliknya, algoritma IKNN menunjukkan peningkatan kinerja yang signifikan dengan nilai Precision, Recall, F1-Score, dan Accuracy mencapai 100% pada seluruh variasi K. Hal ini membuktikan bahwa peningkatan metode KNN melalui pendekatan IKNN mampu menghasilkan klasifikasi sentimen yang jauh lebih akurat dan konsisten. Dengan demikian, IKNN terbukti lebih efektif dan dapat menjadi acuan dalam pengembangan sistem analisis sentimen berbasis kecerdasan buatan di masa mendatang  Kata kunci: PaDi, UMKM, Analisis Sentimen, KNN, IKNN
Co-Authors Adi Putri, Maharani Agus Sevtiana Ahmad Fauzi Akbari, Safitri Alhafidz, Dennis Cesar Amri Amri Amroni Amroni Anggara Putra, Dwi Pasha Asih, Victor Asrul Azhari Muin Aulia, Siti Nur Chairun Nas Chairun Nas Christina, Stefanny Chritviona Parera, Shalom Daphne, Gabrielle Apta Eustacia Elvantonius Elvantonius Erwin Erwin Evi Alvionita Simangunsong Fahrudin, Rifqi Febima, Mesi Fhitriya Fhitriya Fikri Ananda Fransiska Fedelina Christover Goenawan Brotosaputro Gustomi Gustomi Haikal Alfandi Subagyo, Mochammad Harris, Sebastian Ilwan Syafrinal Irfansyah, Ananda Khasanah, Felina Khoirotun Hisan Kresna Adi Pratama Krismeyanto, Samuel Kurniawan, Satria Wahyu Kusnadi Lena Magdalena Lena Magdalena Lena Magdalena Lena Magdalena Lena Magdalena, Lena Magdalena , Lena Marsani Asfi Marsani Asfi Mesi Febima Mita, Shella Muhammad Abdurrohim Muhammad Afif Sulhan Nabillah, Sofy Nakeisha Wahyudi, Nayla Nisa, Nabila Izati Nurfauzi, Yusuf Nurrohmah Nurrohmah Petrus Sokibi, Petrus Putra, Dwi Pasha Anggara Ramdani, Dzahwa Laely Putri Renaldi, Refan Renny Wahyuni Reza Ilyasa Ridho Taufiq Subagio Rizky Maulana Runa, Yohanes Michael Fouk Sahputra, Illal Dwi Sari, Tri Mulia Sherina Natasya Sugandi Siti Nurhaliza Solikhah, Mar'atus Sri Risma Wati Suwandi Suwandi Suwandi Suwandi Suwandi Suwandi Syawaludin, Dwi Febri Sylvia Chandra Tri Vena Meiyanti Turini, Turini Ucu Wardani Oktriana Unang Solihin Valentino, Fernando Winurcahyono, Alexander Yanti, Limbong Aprilina Yulianti Yulianti Zelene, Aurelie