Prof. Magdi El-Bannany - Profile on Academia.edu (original) (raw)

Papers by Prof. Magdi El-Bannany

Leveraging Enhanced Manta-Ray Foraging Optimization with Deep Learning for Maize Diseases Image Classification

Frontiers in Applied Mathematics and Statistics, Jan 2, 2024

Risk management has emerged as a critical element across several economic sectors, with particula... more Risk management has emerged as a critical element across several economic sectors, with particular significance in the banking industry. The governing bodies of these industries encounter a multitude of threats stemming from the escalation of an unpredictable economic environment, the intricacy of transactions and big data, and several other concealed factors. The primary aim of the present research is to investigate the impact of certain financial risks, including capital risk, liquidity risk, and operational risk, on the financial performance of both commercial and Islamic banks operating within the banking sector of the United Arab Emirates. The study will focus on the time frame spanning from to. The data used in this study was sourced from the annual reports of banks, which were acquired from the o cial websites of the Abu Dhabi Securities Exchange and the Dubai stock market. The most prevalent indicators used to assess a bank's financial performance are Return on Assets (ROA) and Return on Equity (ROE). In contrast, the financial risk metrics included three distinct categories of risk: capital risk, liquidity risk, and operational risk. The findings indicate that there is a statistically significant positive relationship between capital risk and both return on assets (ROA) and return on equity (ROE). However, it was observed that neither liquidity risk nor operational risk had a statistically significant impact on either of the financial performance metrics. Moreover, the size of a bank has a notable and favorable impact on both return on assets (ROA) and return on equity (ROE). The ramifications of the study's conclusions have significant importance for regulators, bank management, and investors. IPolicymakers need to prioritize the enhancement of the regulatory framework pertaining to caboutements in order to the financial stability of banks. Bank managers should give priority to the management of capital risk and the size of the bank in order to their financial performance. In order to optimize profits, it is important for investors to carefully evaluate and take into account the many risk considerations associated with their investment selections. JEL: G , G KEYWORDS capital risk, return on assets (ROA), return on equity (ROE), financial performance, Islamic banks, conventional banks, liquidity risk, operational risk Frontiers in Applied Mathematics and Statistics frontiersin.org

Air Traffic Data Analysis Using Recurrent Neural Network (RNN) Classifier During COVID-19

Proceedings of the 6th International Conference on Future Networks & Distributed Systems

Financial distress prediction (FDP) has been a subject of extensive and ongoing research because ... more Financial distress prediction (FDP) has been a subject of extensive and ongoing research because of its significance in both internal and external components of enterprises including investors and creditors. Financial institutions must to be able to foresee financial difficulty in order to allow them for evaluating the financial health of businesses and individuals. Data pre-processing techniques have been found to increase the efficacy of prediction models, and many research consider feature selection as a pre-processing step before creating the models. The creation of efficient feature selection algorithms is one of the main challenges facing FDP. In this study, we present a hybrid methodology for predicting financial distress using a Multi-Layer Perceptron and Genetic Algorithm (MLP_GA) model with boruta automated feature selection. The proposed model is designed on genetic algorithm-based tuning of the crucial MLP hyperparameters, including Network depth, Dense layer activation function, Network width, and Network optimizer for a reliable prediction. This paper investigates how boruta algorithm based feature selection method improve the accuracy of our MLP_GA algorithm. We access the FDP performance utilizing samples of enterprises based in MENA area. Resampling with k-fold evaluation metrics is employed in the experiments. The experimental results indicate that the adoption of the boruta automated feature selection method has significantly enhanced the prediction performance and accuracy of the FDP model.

Journal of Governance and Regulation

It is our pleasure to share some thoughts about how the papers published in the current issue of ... more It is our pleasure to share some thoughts about how the papers published in the current issue of the Journal of Governance and Regulation contribute to the existing related literature with the hope to enable our readers to outline the new and most challenging issues of research in corporate governance and related topics. The papers published in this issue of the Journal of Governance and Regulation have contributed to the ongoing discussion of governance and regulation, and have provided valuable insight into current developments and future prospects in this area. There have been a number of remarkable developments in the field of governance, regulation, and related fields in recent years, which are reflected in the research topics covered in this issue.

Zenodo (CERN European Organization for Nuclear Research), Oct 14, 2022

Purpose-This research aims to understand what factors contributed to the success of Egypt's banki... more Purpose-This research aims to understand what factors contributed to the success of Egypt's banking sector in terms of intellectual capital between 2019 and 2022. Design/methodology/approach-The effectiveness of intellectual capital as a dependent variable is investigated via multiple regression analysis, which examines the association between intellectual capital performance and a number of potential predictors. Findings-The research shows that the intellectual capital performance of Egyptian banks is significantly influenced by the age of the banks, the size of the banks, the structure of the market, and the global financial crisis. Because no comparable empirical study has been undertaken in Egypt before, the findings are crucial. Research Limitations: In order to generalise the findings, more research on the factors that affect the performance of intellectual capital is required. Further, the study's empirical tests were undertaken solely on Egyptian banks during 2019-2022, therefore its conclusions cannot be extrapolated to any other set of banks or any other period of study. Practical implications-The research could help regulators focus on the elements that affect banks' intellectual capital performance, leading to improved efficiency and productivity in the context of value generation. It's helpful for researchers and policymakers in this area because it lays out some principles to follow. Originality/value-This research contributes to the existing body of work on the factors that affect the effectiveness of banks' intellectual capital. Specifically, it investigates the novel ideas that the market structure and worldwide financial crisis affect the productivity of intellectual capital.

Gradient Enhanced Regressive Multivariate Artificial Fish Swarm Optimized Data Collection for IoT-Enabled WSN in Smart Environments

2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS), Feb 1, 2023

International Journal of Financial Studies

Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there ar... more Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there are still concerns regarding its ability to provide Financial Distress Prediction (FDP). An accurate FDP model is required to avoid financial risk at the lowest possible cost. However, in the Internet era, financial data are exploding, and they are being coupled with other kinds of risk data, making an FDP model challenging to operate. As a result, researchers presented several novel FDP models based on ML and Deep Learning. Time series data is are important to reflect the multi-source and heterogeneous aspects of financial data. This paper gives insight into building a time-series model and forecasting distress far in advance of its occurrence. To build an efficient FDP model, we provide a hybrid model (GALSTM-FDP) that incorporates LSTM and GA. Unlike other previous studies, which established models that predicted distress probability only within one year, our approach predicts distress ...

Applied Sciences

This study aims to develop a better Financial Statement Fraud (FSF) detection model by utilizing ... more This study aims to develop a better Financial Statement Fraud (FSF) detection model by utilizing data from publicly available financial statements of firms in the MENA region. We develop an FSF model using a powerful ensemble technique, the XGBoost (eXtreme Gradient Boosting) algorithm, that helps to identify fraud in a set of sample companies drawn from the Middle East and North Africa (MENA) region. The issue of class imbalance in the dataset is addressed by applying the Synthetic Minority Oversampling Technique (SMOTE) algorithm. We use different Machine Learning techniques in Python to predict FSF, and our empirical findings show that the XGBoost algorithm outperformed the other algorithms in this study, namely, Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), AdaBoost, and Random Forest (RF). We then optimize the XGBoost algorithm to obtain the best result, with a final accuracy of 96.05% in the detection of FSF.

FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron

2022 19th International Multi-Conference on Systems, Signals & Devices (SSD)

Earnings Quality in Emerging Economies: The Banks Case

Asia Pacific Business and Economics Conference, Dec 21, 2017

Voluntary Disclosure and True Firm Performance: the Role of Board of Commissioners Effectiveness

Asia Pacific Business and Economics Conference, Dec 21, 2017

A Comparative Analysis of Machine Learning Classifiers and Ensemble Techniques in Financial Distress Prediction

2020 17th International Multi-Conference on Systems, Signals & Devices (SSD), 2020

A company with financial difficulties is referred to as Financially Distressed. The aim of this s... more A company with financial difficulties is referred to as Financially Distressed. The aim of this study is to analyze and compare the machine learning classifiers and ensemble techniques in Financial Distress Prediction. Initial research works in this field use intelligent and linear methods for building predictive models. Most of the research works suggest that data mining methods predict financial distress better than traditional methods. This paper aims at building and evaluating machine learning models including Neural Network (NN), Decision tree (DT), and Support Vector Machine (SVM) for Financial Distress Prediction. This paper also focuses on building a more accurate Prediction model using Ensemble techniques including Majority Voting (MV), Random Forest and AdaBoost ensemble, by combining the outputs of individual classifiers. The machine learning models are built using the dataset containing financial data from UAE firms in the period of 2010–2017.

A Comprehensive Measurement for Sustainability Reporting Quality: Principles-Based Approach

Indonesian Journal of Sustainability Accounting and Management, 2020

This study presents a comprehensive approach to measure sustainability reporting quality (SRQ) an... more This study presents a comprehensive approach to measure sustainability reporting quality (SRQ) and examines levels of SRQ. It was then used to measure SRQ in Indonesia. Based on reporting guidelines, the new comprehensive measurement for SRQ was developed by not only evaluating the extent of disclosures, but also by examining the quality. The content analysis was conducted to measure the level of SRQ using this comprehensive measurement. The samples are from stand-alone sustainability reports of companies. The results indicate that the overall score for SRQ was moderate. The score was derived using five aspects: the extent of quantitative reporting, the extent of qualitative reporting, the content of the report, the quality of the report, and sustainability reporting accordance. This proposed comprehensive SRQ measurement was used to examine the quantitative and qualitative aspects. This measurement will help academicians to examine the quality of reports and provide more credible a...

Economic downturns and working capital management practices: a qualitative enquiry

Qualitative Research in Financial Markets, 2021

Purpose This study aims to explore changes in working capital management (WCM) practices in respo... more Purpose This study aims to explore changes in working capital management (WCM) practices in response to economic downturns, especially during the coronavirus pandemic. Design/methodology/approach This study adopts an interpretative approach. This paper used semi-structured interviews with 2 finance directors and 13 top managers for data collection. This paper used thematic analysis for analysing the interview data. Findings The study findings suggest that the traditional ways of managing working capital may no longer be sufficient during a crisis. Instead, dynamic financing, trade credit policy and continuous staff training to develop new skills are alternative WCM practices to navigate the challenges of a crisis. Further, this paper finds that economic conditions, such as inflation rates, interest rates, exchange rates and government policy, negatively affect WCM. Practical implications The study findings highlight practical issues that may help firms meet their present and future ...

Prediction of Financial Statement Fraud using Machine Learning Techniques in UAE

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), 2021

The purpose of this study is to predict the potential occurrence of financial statement fraud in ... more The purpose of this study is to predict the potential occurrence of financial statement fraud in the United Arab Emirates (UAE) companies using machine learning (ML) techniques in Python, including Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Neural Network (NN) techniques. The data was collected from the UAE Securities and Commodities Authority. The Bloomberg and Osiris databases were also used to collect data for UAE companies, excluding financial firms, for the period from 2010 to 2018. ML techniques in Python were used to predict the potential of financial statement fraud in UAE companies. The results show that SVM, with 89.54% accuracy and a 77.18% F1 score, outperforms all other classifiers, including LR, DT and NN. The findings of the study are significant to businesses that wish to determine the importance of prediction of financial statement fraud using ML techniques. This research project is different from other existing studies because i...

An Ensemble Model for Financial Statement Fraud Detection

Fraudulent financial statements are deliberate furnishing and/or reporting incorrect statistics, ... more Fraudulent financial statements are deliberate furnishing and/or reporting incorrect statistics, and this has become a major economic and social concern as the global market is witnessing an upsurge in financial accounting fraud, costing businesses billions of dollars a year. Identifying companies that manipulate financial statements remains a challenge for auditors, as fraud strategies have become increasingly sophisticated over the years. We evaluate machine learning techniques for financial statement fraud detection, particularly a powerful ensemble technique, the XGBoost algorithm, that help to identify fraud on a set of sample companies drawn from the MENA region. The issue of the class imbalance in the dataset is addressed by applying the SMOTE algorithm. We found that XGBoost algorithm outperformed other algorithms in this study: Logistic Regression (LR), Decision Tree (DT), Vector Machine Support (SVM), Adaboost, and RandomForest. The XGBoost algorithm is then optimised to o...

Cryptocurrency price prediction using traditional statistical and machine-learning techniques: A survey

Characteristics of audit committees and banking sector performance in GCC

Journal of Governance and Regulation, 2021

The purpose of this paper is to investigate the association between bank performance and audit co... more The purpose of this paper is to investigate the association between bank performance and audit committee characteristics for banks in Gulf Cooperation Council (GCC) over the period from 2013 to 2017. Regression of ordinary least squares quantile (OLS) and regression of quantile data are used to test the relationship between bank performance as a dependent variable and certain independent variables. The results revealed that committee size has a significant impact on banks’ performance but the presence of women members, independent members, committee meetings, and the existence of qualified members do not. The current study is one of a few studies, which addresses the association between bank performance and audit committee characteristics for banks in GCC.

A Multi-Layer Perceptron Approach to Financial Distress Prediction with Genetic Algorithm

Automatic Control and Computer Sciences, 2020