Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Journal International Inspire Education Technology (JIIET) Journal of Artificial Intelligence and Technology Information Journal of Applied Informatics Science
Rizki Dewantara
Universitas Islam Negeri Siber Syekh Nurjati Cirebon
Computer Science & IT Control & Systems Engineering Education Engineering Social Sciences

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Comparative Analysis of Hybrid ARIMA-LSTM against Statistical and Machine Learning Benchmarks for Commodity Stock Muhammad Iszul Wilsa; Heru Purnomo Kurniawan; Rizki Dewantara; Dinda Febrihastatiwi; Indri Setiawati
Journal of Artificial Intelligence and Technology Information (JAITI) Vol. 4 No. 2 (2026): Volume 4 Number 2 June 2026
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jaiti.v4i2.260

Abstract

Predicting stock prices in Indonesia’s commodities and energy sectors is a complex challenge due to high volatility influenced by global market dynamics and macroeconomic factors. This study aims to test the robustness of the ARIMA-LSTM hybrid model in predicting closing stock prices for six major issuers: ADRO, PTBA, MEDC, ANTM, MDKA, and AALI. The proposed approach employs a dual-input strategy that integrates 27 technical indicators with the linear residuals from the ARIMA model. The research methodology begins with data decomposition using the ARIMA model to capture linear components, followed by modeling the residuals using Long Short-Term Memory (LSTM) to capture complex non-linear patterns. The experimental results show that the hybrid model consistently delivers the best performance compared to single models such as ARIMA, Random Forest, and Single LSTM across all test datasets. In the 1-step-ahead scenario, the hybrid model achieved the lowest average MAPE of 2.20%, while in the 5-step-ahead scenario, the error rate remained at 3.98%. A key finding of this research is the hybrid architecture’s ability to mitigate the extreme overfitting experienced by the Single LSTM model, while providing better prediction stability against variations in issuer characteristics. This study concludes that the integration of statistical decomposition and deep learning provides a reliable framework for investors and analysts to make data-driven decisions amid the volatile fluctuations of the Indonesian capital market.
Analisis Ancaman Perang Siber terhadap Keamanan Nasional Indonesia: Tinjauan Eskalasi dan Mitigasi Tahun 2025 Rizki Dewantara; Gina Khayatun Nufus; Eko Jhony Pranata; Fariz Noor Djati
Journal of Applied Informatics Science Volume 2 Issue 1 (2026)
Publisher : GWS Tech Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65897/jais.v2.i1.80

Abstract

Kemajuan teknologi internet telah menciptakan interkoneksi global yang memicu ancaman perang siber terhadap keamanan nasional. Masalah utama yang dihadapi Indonesia adalah tingginya kerentanan terhadap serangan digital, dengan catatan tiga koma enam puluh empat miliar anomali trafik pada awal dua ribu dua puluh lima. Penelitian ini bertujuan untuk menganalisis berbagai jenis, tingkat bahaya, dan dampak serangan siber dalam mengganggu stabilitas kedaulatan negara. Metode penelitian yang digunakan adalah kualitatif non interaktif melalui pengkajian dokumen sekunder dari jurnal ilmiah dan laporan resmi otoritas siber. Hasil penelitian menunjukkan adanya fluktuasi anomali trafik yang signifikan dengan puncak tertinggi mencapai enam ratus lima belas koma empat juta kejadian pada Juni dua ribu dua puluh lima. Tren serangan mulai bergeser dari eksploitasi teknis menuju rekayasa sosial yang menyasar celah psikologis pengguna. Kesimpulannya, Indonesia masih berada dalam kategori negara rentan sehingga diperlukan penguatan regulasi serta peningkatan kapasitas sumber daya manusia untuk menghadapi evolusi ancaman siber.
XSentiment-HS: Hierarchical CNN-BiGRU-SVM with Explainable for Indonesian Multi-Level Hate Speech Detection Gina Khayatun Nufus; Rizki Dewantara; Ardi Susanto; Sokid; Lia Farhatuaini; Jaka Septiadi; Mohammad Raihan Akbar
Journal of Applied Informatics Science Volume 2 Issue 1 (2026)
Publisher : GWS Tech Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65897/jais.v2.i1.81

Abstract

Deteksi ujaran kebencian pada media sosial menuntut interpretasi teks yang kompleks karena sifatnya yang spontan dan ambigu, terutama dalam bahasa Indonesia yang kaya akan slang. Tantangan utama saat ini adalah keterbatasan penelitian sebelumnya yang mayoritas hanya melakukan klasifikasi biner tanpa mendeteksi tingkat keparahan konten. Penelitian ini mengusulkan XSentiment-HS, sebuah model deep learning hierarkis dua tahap untuk deteksi multi-tingkat hate speech. Arsitektur model menggabungkan Convolutional Neural Networks (CNN) untuk ekstraksi fitur lokal dan Bidirectional Gated Recurrent Unit (BiGRU) untuk menangkap ketergantungan kontekstual jangka panjang. Model ini juga diperkuat dengan mekanisme Multi-Head Attention dan Support Vector Machine (SVM) sebagai classifier final. Melalui integrasi ini, XSentiment-HS diharapkan mampu mengatasi tantangan ekstraksi fitur dan polisemi secara lebih efektif dibandingkan metode konvensional.
THE ROLE OF BLOCKCHAIN IN DIGITAL CREDENTIALS AND THE FUTURE OF EDUCATION CERTIFICATION Rizki Dewantara; Amin Zaki; Faisal Razak
Journal International Inspire Education Technology Vol. 5 No. 3 (2026)
Publisher : Sekolah Tinggi Agama Islam Al-Hikmah Pariangan Batusangkar, West Sumatra, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55849/jiiet.v5i3.1299

Abstract

Digital transformation has accelerated the adoption of electronic credentials, online certifications, and lifelong learning records across educational institutions worldwide. Growing concerns regarding credential fraud, verification inefficiencies, data security, interoperability, and learner ownership have highlighted the limitations of traditional and centralized certification systems. Blockchain technology has emerged as a promising solution capable of enhancing trust, transparency, and security in educational credential management. This study aims to examine the role of blockchain in digital credentials and explore its implications for the future of education certification. A mixed-methods research design employing a sequential explanatory approach was utilized. Quantitative data were collected from 420 stakeholders, including university administrators, educational technology specialists, employers, policymakers, and graduates. Qualitative interviews were conducted with selected participants to gain deeper insights into implementation opportunities and challenges. Structural Equation Modeling and thematic analysis were employed to analyze the data. Findings revealed that perceived security significantly influenced trustworthiness, while trustworthiness emerged as a strong predictor of adoption intention. Interoperability positively affected institutional readiness and supported efficient credential exchange across educational and professional environments. Qualitative evidence further demonstrated improvements in verification efficiency, credential portability, learner empowerment, and stakeholder confidence. The study concludes that blockchain technology has substantial potential to transform educational certification systems by creating secure, transparent, learner-centered, and globally interoperable credential ecosystems capable of supporting future educational and workforce demands.
Co-Authors Amin Zaki Ardi Susanto Dinda Febrihastatiwi Eko Jhony Pranata Faisal Razak Farhatuaini, Lia Fariz Noor Djati Gina Khayatun Nufus Indri Setiawati Jaka Septiadi Kurniawan, Heru Purnomo Mohammad Raihan Akbar Muhammad Iszul Wilsa Sokid