Al-Zaytoonah University Journal of Business

A Comparative Study of Machine Learning and Deep Learning Algorithms for Student Dropout Prediction in Higher Education

2026-04-05T20:05:08+00:00

Abstract Student dropout in higher education represents a significant academic and economic challenge. This study investigates the effectiveness of machine learning and deep learning techniques for early identification of at-risk students. A two-stage experimental framework is proposed. In the first stage, three machine learning algorithms (Random Forest, Support Vector Machine, and XGBoost) are compared with two deep learning models (Deep Neural Networks and TabNet) using the original dataset. In the second stage, the impact of data balancing techniques, namely SMOTE and Borderline-SMOTE, is evaluated. Model performance is assessed using accuracy, precision, recall, and specificity. The results demonstrate that XGBoost consistently achieves superior performance across both imbalanced and balanced datasets, while data balancing techniques significantly improve recall, enhancing the detection of at-risk students. These findings provide valuable insights into the role of data balancing in improving predictive performance in student dropout prediction.

Comprehensive Multi-Agent Distributed Artificial Intelligence Framework in Higher Education

2026-04-06T19:50:02+00:00

A framework of a multi-agent system will be designed to enhance teaching and learning processes in higher education, aligning with Sustainable Development Goal 4(SDG 4). It emphasizes the roles of various intelligent agents, such as Student Agents and Instructor Agents, which work collaboratively to improve learning outcomes and student engagement. The framework leverages artificial intelligence to address complex educational challenges while ensuring effective communication among agents. Additionally, it highlights the importance of data protection measures to mitigate risks associated with unauthorized access and algorithmic bias.

Does Supply Chain Analytics Impact Supply Chain Agility and Competitive Advantage? The Mediating Role of Robustness Capability

2026-04-06T20:03:20+00:00

The present study has focused on analyzing the impact of Supply Chain Analytics (SCA) on supply chain agility and competitive advantage by investigating the mediating role of robustness capability in Jordanian pharmaceutical manufacturing. The sample population included professionals at the supply chain and logistics department levels. Since a random sampling technique was followed, data was collected through structured questionnaires. This analysis was conducted through SmartPLS 4.0 and tested the discriminant and convergent validity of the measurement model. From this, one can find out that SCA significantly impacts Supply Chain Agility (β = 0.602, p < 0.001) and Competitive Advantage (β = 0.238, p < 0.01). In addition, Robustness Capability was also another imperative mediator in those relationships, improving the general effect of SCA on the investigated outcomes with mediation effects of β = 0.103 (p < 0.05) for Supply Chain Agility and β = 0.285 (p < 0.001) for Competitive Advantage. Results thus indicate that firms should focus on integrating SCA with robust strategies that guarantee agility for sustained competitive advantage in the volatile Jordanian Pharmaceutical Industry.

The Impact of AI-Driven Risk Management on Earnings Management: Empirical Evidence from Jordan’s Industrial Sector

2026-04-06T20:10:45+00:00

This article analyzes the influence of AI-managed risks on employment manipulation (EM) within a Jordanian industrial firm. To guarantee comprehensive representation, 312 interviews were conducted with industry professionals possessing diverse responsibilities, organizational sizes, and demographic backgrounds via a standardized survey from March 2025 to May 2025. To validate and ensure the reliability of the findings, the research employed PLS-SEM with an adequate sample size. The results indicate that the proper integration of AI-driven risk management into operations substantially influences earnings management. The findings indicate that risk management plays a pivotal role in influencing financial reporting and discretionary accounting practices as an intermediary factor in the indirect relationship between AI deployment and earnings management outcomes. The function of AI in the regulation and implementation of earnings commodities strategies, a topic that has received less empirical focus in emerging nations like Jordan, addresses a significant gap in the literature. The findings indicate that AI improves operational efficiency, mitigates the risks of financial fraud, and strengthens regulatory compliance, impacting the three phases of planning, execution, and monitoring. These results increase the integration of theory and practice by providing distinct insights into the deployment of AI to influence earnings management, improve transparency, and ensure long-term financial sustainability in industrial firms.

The Role of Waqf as a Sustainable Non-Profit Institution for Socio-Economic Development

2026-04-05T13:10:03+00:00

Waqf has historically played an important role in supporting social welfare and economic development across many Islamic societies. As a charitable endowment institution, Waqf has contributed to financing education, healthcare, infrastructure, and community services for centuries. In recent years, increasing attention has been directed toward the potential role of Waqf as a sustainable mechanism for addressing contemporary socio-economic challenges such as poverty, inequality, and limited public resources. This study examines the role of Waqf as a sustainable non-profit institution and explores its potential contribution to socio-economic development. The study adopts a qualitative conceptual research design based on a comprehensive review and analysis of relevant literature on Waqf, nonprofit organizations, Islamic social finance, and sustainable development. The findings indicate that Waqf institutions possess significant potential to function as sustainable philanthropic organizations capable of generating long-term financial resources for community development and social welfare. The analysis also highlights that the effectiveness of Waqf institutions depends largely on the adoption of modern governance frameworks, professional management practices, and supportive regulatory environments. Furthermore, integrating Waqf with other Islamic social finance instruments and adopting innovative approaches such as cash Waqf and digital platforms can significantly enhance its developmental impact. This study contributes to the growing literature on Islamic social finance by presenting Waqf as a sustainable non-profit model capable of supporting inclusive socio-economic development in modern societies. The study also provides policy recommendations aimed at strengthening the governance, management, and institutional effectiveness of Waqf institutions.

The Effect of Cash Holdings on Non-Audit Services Fees "An Empirical Study on the Industrial Public Shareholding Companies in Emerging Countries"

2026-04-05T20:15:43+00:00

The aim of this study was to investigate the effect of cash holdings on Non- Audit services Fees in Jordanian public Shareholding industrial companies, the study used the relational descriptive approach in order to collect data and analyse it quantitatively, aiming to describe independent and dependent variables and to reveal predictive correlations among them, the study used the arithmetic averages, the standard deviations, and the log linear regression test for each of the study variables. The study was applied to a sample consisting of (44) companies listed on the Amman stock Exchange in the industrial sector during the period (2022-2024).The study reached a set of results, namely, that cash holdings clearly affect Management consulting services, as for tax services, the study showed that there is no relationship between cash holdings and tax services, this may be due to the fact that tax services do not predict cash holdings in Jordanian public Shareholding industrial Companies. The most important Recommendations, Determine the amount of cash holdings that companies must maintain and impose more control on companies to reduce the possibility of fraud and misrepresentation in the financial statements, and the necessity of working to determine the amount of non-Audit fees according to objective principles and obliging companies to disclose non-audit services in the annual reports.

Artificial Intelligence and Deep Learning for Sustainable Health Systems in Jordan: A Policy and Implementation Framework

2026-04-06T20:19:31+00:00

Abstract The role of artificial intelligence (AI) and deep learning (DL) in enhancing health systems is becoming more actively studied, especially in the areas where the delivery of services is uneven and the data systems are decentralized. These problems are reflected in maternal and child morbidity, nutrition, and regional differences in care access in Jordan. The article develops a theoretical and policy-oriented model of AI implementation in the Jordanian national health care.

According to the results of the Jordan Population and Family Health Survey (2023) and the most recent literature, the study aims at four areas, which include mortality risk prediction, maternal and perinatal health, nutrition monitoring, and disability-sensitive spatial planning. It evaluates the right AI strategies, data requirements and implementation feasibility.

As stated in the discussion, AI can enhance the early identification of risks, intervention targeting, and planning reinforcement. However, it needs to be integrated with data, institutional preparedness, governance, and ethical concerns to be successful in its adoption. In order to apply responsibility and context-sensitive implementation, a roadmap is proposed in phases.