Garuda - Garba Rujukan Digital

Enhancing Market Trend Analysis Through AI Forecasting Models Rosa Lesmana; Indra Wijaya; Efa Ayu Nabila; Harry Agustian; Sipah Audiah; Adam Faturahman
International Journal of Cyber and IT Service Management (IJCITSM) Vol. 4 No. 2 (2024): October
Publisher : International Institute for Advanced Science & Technology (IIAST)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/ijcitsm.v4i2.162

Accurate market trend analysis is crucial for strategic decision making in industries, yet traditional forecasting models often struggle to provide reliable predictions in rapidly changing environments. This study investigates the application of advanced Artificial Intelligence (AI) models Long Short Term Memory (LSTM), Random Forest, Decision Trees, and Support Vector Machines (SVM) to improve the accuracy and robustness of market forecasting. Data was collected from sources like Bloomberg and Yahoo Finance, encompassing stock prices, economic indicators, and sector specific trends over five years. The models were evaluated using metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) to assess their predictive performance. Results show that AI models, especially LSTM, outperform traditional models like Auto Regressive Integrated Moving Average (ARIMA), offering superior handling of complex temporal dependencies and short term market fluctuations. For instance, LSTM achieved a MAPE of 1.8% and RMSE of 0.045, significantly improving forecast precision over ARIMA. Random Forest and Decision Trees also provided valuable insights into market drivers, adding interpretability to the forecasting process. This research highlights the potential of AI to enhance decision making by offering more accurate, data driven predictions and provides practical guidelines for implementing these models in real world market forecasting. Future research should explore hybrid AI approaches and broader datasets to further enhance forecasting adaptability across diverse market conditions.

Enhancing Market Trend Analysis Through AI Forecasting Models Rosa Lesmana; Indra Wijaya; Efa Ayu Nabila; Harry Agustian; Sipah Audiah; Adam Faturahman
International Journal of Cyber and IT Service Management (IJCITSM) Vol. 4 No. 2 (2024): October
Publisher : International Institute for Advanced Science & Technology (IIAST)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/ijcitsm.v4i2.162

Accurate market trend analysis is crucial for strategic decision making in industries, yet traditional forecasting models often struggle to provide reliable predictions in rapidly changing environments. This study investigates the application of advanced Artificial Intelligence (AI) models Long Short Term Memory (LSTM), Random Forest, Decision Trees, and Support Vector Machines (SVM) to improve the accuracy and robustness of market forecasting. Data was collected from sources like Bloomberg and Yahoo Finance, encompassing stock prices, economic indicators, and sector specific trends over five years. The models were evaluated using metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) to assess their predictive performance. Results show that AI models, especially LSTM, outperform traditional models like Auto Regressive Integrated Moving Average (ARIMA), offering superior handling of complex temporal dependencies and short term market fluctuations. For instance, LSTM achieved a MAPE of 1.8% and RMSE of 0.045, significantly improving forecast precision over ARIMA. Random Forest and Decision Trees also provided valuable insights into market drivers, adding interpretability to the forecasting process. This research highlights the potential of AI to enhance decision making by offering more accurate, data driven predictions and provides practical guidelines for implementing these models in real world market forecasting. Future research should explore hybrid AI approaches and broader datasets to further enhance forecasting adaptability across diverse market conditions.

Governance Models for Blockchain Integrated IoT Ecosystems Rizki Indrawan; Arista Ratih; Harry Agustian; Richard Evans
Blockchain Frontier Technology Vol. 5 No. 2 (2026): Blockchain Frontier Technology
Publisher : IAIC Bangun Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/bfront.v5i2.974

The rapid advancement of the Internet of Things (IoT) has led to the creation of large-scale interconnected networks of smart devices capable of autonomously collecting, processing, and exchanging data in real time across diverse application domains. While this development offers significant benefits, it also introduces critical challenges related to data security, privacy protection, interoperability, and the increasingly complex governance of distributed IoT systems. Traditional centralized governance approaches often fail to address these issues effectively due to single points of failure, limited transparency, and insufficient trust mechanisms. The integration of blockchain technology into IoT ecosystems provides a promising alternative by leveraging decentralized architecture, immutable ledgers, transparency, and tamper-resistant features that enhance accountability and trust. This study aims to identify and design an appropriate governance model for blockchain-integrated IoT systems that balances security, operational efficiency, and decentralization. The research adopts a conceptual and qualitative approach through a systematic literature analysis and the synthesis of existing governance, blockchain, and IoT frameworks to develop a structured governance model. The proposed framework defines institutional roles, policy structures, decision-making processes, and control mechanisms among participating entities. The results demonstrate that a blockchain-based governance model enhances system security, operational efficiency, and inter-organizational trust by reducing reliance on centralized authorities and improving data integrity. In addition, the use of smart contracts enables automated policy enforcement, transparent coordination, and sustainable system operations, supporting scalable and resilient governance for future blockchain IoT ecosystems.

Sharia-Guided Artificial Intelligence for Ethical Transformation in Modern Education Muchlishina Madani; Harry Agustian; Adam Faturahman; Asep Sutarman; Ramiro Santiago Ikhsan
Jurnal MENTARI: Manajemen, Pendidikan dan Teknologi Informasi Vol 4 No 2 (2026): March
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/mentari.v4i2.975

The rapid advancement of digital technologies has accelerated the integration of Artificial Intelligence (AI) into educational systems worldwide. Despite its benefits, concerns about ethics, algorithmic bias, transparency, and value alignment remain significant, particularly in faith-based educational institutions that emphasize moral and spiritual development. This study aims to propose a Sharia-Guided Artificial Intelligence (SGAI) model that supports ethical, accountable, and value-oriented transformation in modern education. The research employs a mixed-method approach by combining qualitative analysis of Islamic educational principles and ethical frameworks with quantitative evaluation of AI-supported governance practices in educational institutions. Data were collected from educators, administrators, and students within Islamic educational environments to assess the feasibility, acceptance, and integrity of AI implementation within a Sharia-compliant framework. The results indicate that AI systems guided by Sharia principles can improve curriculum personalization, administrative efficiency, transparency, and institutional accountability while reducing algorithmic bias and maintaining ethical values in educational processes. Furthermore, the proposed model encourages responsible data governance, ethical decision-making, and inclusive learning environments supported by intelligent technologies. The integration of intellectual, ethical, social, and spiritual dimensions also strengthens holistic educational development. In conclusion, embedding faith-based ethical intelligence into AI-driven educational management can foster sustainable, trustworthy, and socially responsible innovation while providing a practical framework for value-aligned AI adoption in education.

Blockchain Applications for Transparency in the Insurance Industry Chandra Lukita; Harry Agustian; Kamal Arif Al-Farouqi; Fazri Arkiman
AI, Innovation, and Resilience for the Environment (AIR) Vol. 1 No. 1 (2026): AI, Innovation, and Resilience for the Environment (AIR) Journal
Publisher : Sinar Mentari Sundara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68012/air.v1i1.122

Transparency has become a critical pillar for trust in the insurance industry, yet traditional systems remain plagued by opaque claim procedures, high fraud rates, and inefficiencies caused by centralized databases. This study aims to analyze how blockchain-based mechanisms can address key pain points in claims processing, fraud detection, and data integrity. Adopting a conceptual and qualitative research approach, the methodology synthesizes findings from academic publications, industry reports, and real-world implementations to evaluate blockchain's contribution across four dimensions: process transparency, operational efficiency, trust, and regulatory compliance. The results indicate that core blockchain attributes—such as smart contracts and immutable ledgers significantly accelerate claim settlements, reduce information asymmetry, and enable real time behavior tracking through technologies like the Internet of Vehicles (IoV). It is concluded that while challenges regarding privacy and regulatory fragmentation persist, blockchain offers a paradigm shift toward a more transparent, efficient, and trustworthy insurance ecosystem by realigning economic incentives between insurers and policyholders.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search