This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

Purpose: The paper aims to study the methodology and functional of Internal Audit (IA) during the transition to remote working methods necessitated by the COVID-19 pandemic crisis period. Design/methodology/approach: Data are collected over a sample of 352 internal audit departments in retail SMEs distributed in the Gulf Cooperation Council (GCC) region. The six variables are measured using a reflective model. An exploratory factor analysis is applied to gauge the measurement model’s validity and reliability. Findings: The research findings revealed that internal auditing within the Kingdom of Saudi Arabia (KSA) and the Qatari retail sector is not sufficiently advanced. The focus of internal auditing primarily revolves around compliance audits rather than performance audits, thereby limiting their degree of agility and strategy which negatively affects the IA methodology. Conversely, for the United Arab Emirates (UAE) retail companies the research hypotheses were validated showing an IA functions evolution, an IA reassurance and IA agility that are conducted throughout a remote working and a strategic design that affect positively IA working methodology. Originality: The originality impregnates by the fact that reviews of traditional audit working methods were updated and shaped according to the deficiencies that couldn’t be identified during a pre COVID-19 period. A traditional audit plan may not work in this situation. The originality of the study consists of estimating IA methodological review through an agile approach that provides internal reassurance and risk attenuation.

The dairy industry is considered one of the most needed industries in almost every country; this is due to the continuous daily demand of its different products. Nevertheless, this industry consumes large amount of water, energy and material resources, and generates large quantities of liquid and solid wastes. In the sequel, under the pressure of fulfilling the 17 sustainable development goals (17 SDGs), it is important to address the sustainability of this sector in the world and particularly in developing countries. This study aims at assessing the impact of environmental, economic and social sustainability practices on the organizational performance of dairy industry in Palestine. To this end, a quantitative-research approach, based on a questionnaire for data collection, was adopted. Data has been collected from a convenient sample of 15 dairy factories working in West Bank in Palestine during a three-month period from March to May, 2023. Inferential statistical analyses were conducted as well. The results revealed that there is a difference between the median values of environmental and economic practices. In addition, the results showed that there is a medium relationship between sustainability practices and organizational performance. However, the economic practices proved to have the strongest impact then social practices; while, there is no impact of environmental practices on organizational performance. Furthermore, the results showed that this industry consumes larger amount of water as well as it generates large amounts of wastewater that mainly discharged to the drainage system without treatment for recycling or reuse. Several sound recommendations are given at the end of this paper. It worth mentioning that there are no previous studies conducted on the dairy industry sector in Palestine about sustainability assessment.

The presence of a crisis has consistently been an inherent aspect of the Supply Chain, mostly as a result of the substantial number of stakeholders involved and the intricate dynamics of their relationships. The objective of this study is to assess the potential of Big Data as a tool for planning risk management in Supply Chain crises. Specifically, it focuses on using computational analysis and modeling to quantitatively analyze financial risks. The “Web of Science—Elsevier” database was employed to fulfill the aims of this work by identifying relevant papers for the investigation. The data were inputted into VOS viewer, a software application used to construct and visualize bibliometric networks for subsequent research. Data processing indicates a significant rise in the quantity of publications and citations related to the topic over the past five years. Moreover, the study encompasses a wide variety of crisis types, with the COVID-19 pandemic being the most significant. Nevertheless, the cooperation among institutions is evidently limited. This has limited the theoretical progress of the field and may have contributed to the ambiguity in understanding the research issue.