Search Results for z-score
Abstract
Given the swift digital changes occurring in the Banking industry, the purpose of this paper is to examine how well artificial intelligence systems can forecast and protect against future disasters. By utilizing its skills in big data analytics, forecasting financial behavior, and more accurately and effectively managing risks, artificial intelligence (AI) is increasingly regarded as a crucial component in the development of banking systems and improving their operational efficiency.
By enhancing client satisfaction, tailoring banking services to meet the demands of each individual, and cutting down on operational errors and administrative expenses, banks hope to gain a competitive edge by utilizing these technologies. AI also helps to speed up credit decisions, make it possible to identify financial crime early, and create clever marketing plans based on forecasts of future market trends.
In order to ensure financial sustainability and achieve integration between digital transformation and the demands of banking innovation, studies show that the future of AI encompasses strategic, cultural, human, technological, and organizational dimensions in addition to technical ones.
The paper also examined a number of anticipated long-term effects of AI applications, such as increased forecasting precision, lower operating expenses, better customer satisfaction, increased worker productivity, and assistance with investment choices. The findings show that implementing AI applications in the banking sector is a strategic requirement to guarantee long-term growth and competitiveness in the digital era, not a technical luxury.
In order to enhance lending decisions and lower default risks, the paper also assesses how well a number of categorization algorithms work in assessing loan applicants' creditworthiness. Using a dataset that represented the traits and financial activities of clients, seven machine learning techniques were used: Gradient Boosting, Random Forest, Extra Trees, Gaussian Naive Bayes, Logistic Regression, SVC-RBF, and KNN.
The paper used a database of 21 variables for loan applicants. Numerical variables included (age, income, credit score, debt-to-income ratio, and loan amount). Descriptive variables included (loan purpose, region, marital status, employer, educational level, and application channel). Binary variables included (whether or not the applicant had a history of default). These variables were used to predict the approval or rejection decision, with the dependent variable being represented by two values: 0 for rejection and 1 for approval.
The models were evaluated using the following six key performance indicators: Accuracy, Precision, Recall, F1 Score, Receiver Operating Characteristic Area Under the Curve (ROC AUC), and Brier Score. The findings demonstrated that the Gradient Boosting algorithm performed best overall in both probability prediction quality and customer differentiation across different risk levels. The Random Forest algorithm, which showed stability and balanced metrics, came next. On the other hand, despite its moderate performance, Logistic Regression provided great interpretability, while the Gaussian Naive Bayes algorithm demonstrated high sensitivity in identifying high-risk customers. In terms of overall accuracy and probability quality, some models—like SVC-RBF and KNN—performed worse.
Abstract
This study presents a machine learning-based framework for predicting and analyzing student academic performance using behavioral, psychological, demographic, and digital learning features. The dataset consists of 14,003 student records collected from higher education institutions in 2024 and obtained from Kaggle. It includes 16 variables covering study behaviors, engagement patterns, learning resources, psychological factors, and demographic characteristics. The target variable (response) was Final Grade, which was categorized into four performance levels: Low / Fail / Poor performance, below average performance, Good / Average performance, and Excellent / High performance, representing overall academic performance. Three machine learning algorithms XGBoost (Extreme Gradient Boosting), CatBoost (Categorical Boosting), and Support Vector Machine (SVM) were applied to classify student performance levels. The models were evaluated using confusion matrices, accuracy, F1-score, MCC, R², RMSE, MAE, and feature importance analysis. Results show that XGBoost achieved the highest performance (99.96% accuracy), followed by CatBoost (99.82%) and SVM (98.96%). Analysis of the importance analysis revealed that Exam Score is the most influential predictor across all models. The study highlights the effectiveness of advanced machine learning techniques in predicting academic success and supporting data-driven educational decision-making.
Abstract
Problem Statement: economic environment differs than before, due to the rapid strategic changes and high level of demand for qualified services and/ or goods, that leads to another sense of competing among businesses, especially in last decades of 20th century, business environment involved in globalization to response and satisfy customers depending on the interaction between society as (external environment) and business’s infrastructure as (internal environment). These changes need a rapid response that means using new systems in planning strategies, organizing, leading and controlling as well to sustain and survive.
Methodology: it is a descriptive paper that analyze the results through depending on non- experimental design through three (retrospective, longitudinal, and cross- sectional) indicators to examine environmental social responsibility ESP as one of balanced score card perspectives. Results: there is a positive impact of adopting ESRP to achieve qualified financial projects. Conclusion: the interlinkage between external environment (society) and internal one (business infrastructure) is very tight, but the horizon to understand this tight relationship is still fuzzy, due to the dynamic changes of those interlinkages and more efforts have to be done to enrich this phenomenon.
Abstract
The current study examines the impact of income diversification on the profitability and stability of Jordanian commercial banks. The study sample consisted of (13) commercial banks operating in Jordan for the period 2010-2022. The secondary data included in the financial reports and annual budgets issued by the Jordanian commercial banks are also considered. The study employs the ratio of non-interest income to total operating income and the Hirschman-Herfindahl index to measure income diversification, while the return on assets and return on equity indices were used to measure bank profitability. To measure financial stability, the z-score value was calculated. The Panel Data regression model was employed, and the random effect model was chosen to test the study hypotheses. The results showed that the ratio of non-interest income has a positive and significant impact on the profitability of Jordanian commercial banks. This indicates that increasing reliance on non-interest income sources enhances the performance and profitability of Jordanian commercial banks. The results also showed that the HHI index has a positive and significant effect on the profitability and stability of Jordanian commercial banks, which means that increasing the level of diversification in income sources leads to increased profitability and financial stability in Jordanian commercial banks. The study recommended the necessity of encouraging commercial banks to innovate financially and provide digital banking services and other non-traditional services due to their role in increasing profits and financial stability in Jordanian commercial banks.
Abstract
The research aims to understand the change in capital structure and its impact on financial stability, clarifying its features for decision-makers, thus enabling them to make sound decisions, especially investors. One of the most important objectives of the research was to determine the financial stability of the research sample during the research period, relying on the Altman model adopted in the financial stability process. The sample included five banks: (Bank of Baghdad, Bank of Babylon, Gulf Bank, United Investment Bank, and Sumer Bank). The research period was from 2015 to 2019. The researchers relied on financial analysis to present the results and clarify the nature of the relationship between the two variables. They reached a number of results, the most important of which is that the change in capital structure leads to an impact on the financial stability of the banks in the research sample. One of the most important recommendations reached by the research is the necessity of maintaining the capital structure from changes affecting it by relying on attracting investors, especially from outside the country.
Abstract
The process of pricing bank loans is one of the most important sources for the bank’s
revenues, as loans represent a large part of the bank’s assets. The research aims to measure and
know the impact of bank loan pricing indicators on credit risk. When the bank sets a high interest
rate, this leads to a loss of customers by going to other banks to obtain loans, and if a low interest
rate is set, this leads to a loss for the bank. Therefore, banks should use modern methods of
pricing bank loans. The research community represents the banks listed in the market. Iraq Stock
Exchange. As for the research sample, it consisted of 8 banks that were selected from among 24
banks listed on the Iraq Stock Exchange that meet the research requirements, and for the period
(2006-2015), and a set of financial indicators were used (return on net funds used, weighted
average cost of capital, Z-Score Profitability objective) Measurable research variables .
Abstract
This study aimed to identify the role of the financing structure variables in reducing the financial fragility of private commercial banks. Bank operation and continuity. In its practical aspect, the study relied on a set of published financial reports and statements for two of the banks listed in the Iraqi Stock Exchange for the period between 2005 - 2019. And to test its main hypothesis, multiple regressions was used in the method of regressive deletion. The study reached a set of results, perhaps the most important of which is that there is a statistically significant inverse effect between ownership finance and financial fragility in the study sample banks. Traditional and modern hedging mechanisms that help it get rid of fragility, as well as the application of the Altman model to measure financial fragility and determine its financial position.
Abstract
The research aims to shed light on the stages of development of the balanced score card to the sustainable balanced score card. And according to what the sustainable balanced scorecard contains of many non-financial indicators in its three perspectives except for the financial one, so the research aimed to employ the card and identify its indicators, which usually function as a performance evaluation, so that those same indicators are the non-financial information that is disclosed within The integrated report model, which represents the most advanced generation of reporting.
The electronic payment card company Qcard was chosen to implement the proposed research model. As its financial and administrative reports were analyzed, in addition to conducting extensive interviews with the heads of various departments in the company, the sample of the research. The indicators that formed the sustainable balanced scorecard and which later represented the guide for preparing the integrated report form were identified after distributing the indicators that represent non-financial information on the nine components of the integrated report form.
And the most important conclusion was the operation of non-financial information, in addition to financial information, which led to the activation of management accounting tools, facilitating the formulation of the strategy of the economic unit, the implementation of the strategic objectives of the economic unit, and the achievement of sustainability requirements. Its performance from multiple points of view and enabled the management accountant and management to quantify expectations to the nearest degree of accuracy, which leads to correcting the evaluation process and expanding the area of correction options that can be put forward in the strategic performance evaluation process. As for the most important recommendation, it was necessary to unify the efforts of academics and professionals to raise the level of application of management accounting tools in economic units, and to employ those tools in enabling units to achieve sustainability requirements, and the consequent necessity of developing management accountant skills in preparing reports that feed departments with information. Necessary to fulfill these requirements.
Abstract
This study aimed to examine the role of organizational identity in enhancing strategic cohesion at Al-Furat General Company for Chemical Industries by assessing the level of organizational identity and its dimensions, as well as investigating the nature of the relationship and impact between organizational identity and strategic cohesion. The study adopted a descriptive-analytical approach and employed a structured questionnaire as the primary data collection instrument. Data were collected from a sample of 239 employees and analyzed using SPSS Version 26. The statistical techniques included descriptive statistics, Pearson's correlation coefficient, and simple linear regression analysis. The findings revealed a high level of organizational identity, with a mean score of 3.94, while the level of strategic cohesion was found to be satisfactory, with a mean score of 3.76. The results further indicated a positive and statistically significant correlation between organizational identity and strategic cohesion (r = 0.671, p < 0.01). Moreover, organizational identity exerted a positive and significant effect on strategic cohesion, explaining 45.1% of the variance in the dependent variable. Among the dimensions of organizational identity, continuity demonstrated the strongest effect, followed by distinctiveness and centrality. The study concluded that strengthening organizational identity constitutes an effective strategic approach to enhancing strategic cohesion and achieving greater alignment between organizational vision, strategic objectives, and managerial practices. Accordingly, the study recommends reinforcing organizational identity values, sustaining organizational continuity, improving internal communication systems, and promoting employees' participation in the implementation of strategic initiatives to enhance organizational performance.
Abstract
Breast cancer is one of the most prevalent and life-threatening diseases worldwide, making early and accurate diagnosis essential for improving patient outcomes. This study aims to evaluate the performance of two machine learning models, Extreme Gradient Boosting (XGBoost) and Gaussian Naive Bayes, for breast cancer classification using the Breast Cancer Wisconsin Diagnostic dataset. A comparative analysis was conducted based on several performance metrics, including Accuracy, Precision, Recall, F1-score, Specificity, Receiver Operating Characteristic (ROC) curve, Area Under the Curve (AUC), Balanced Accuracy, and Confusion Matrix. In addition, feature importance analysis was performed to identify the most influential variables contributing to the classification process. The experimental results demonstrated that both models achieved high classification performance. However, the Gaussian Naive Bayes model showed slightly superior performance, achieving an Accuracy of 96.5% and an AUC of 0.997, compared with 96.0% and 0.993, respectively, for the XGBoost model. Furthermore, the analysis revealed that features related to tumor morphology, particularly concave points mean, perimeter worst, and radius worst, were among the most influential predictors of breast cancer classification. The findings indicate that both machine learning models provide reliable and effective tools for supporting early breast cancer diagnosis, with Gaussian Naive Bayes demonstrating a slight advantage for the dataset used in this study. These results highlight the potential of machine learning techniques to enhance diagnostic accuracy and support clinical decision-making.