Search Results for Khalid A. khider
Abstract
This study aimed to evaluate the financial sustainability of Iraqi industrial companies using machine learning models and to compare their performance with traditional statistical models. Five key financial variables were analyzed: Working Capital Ratio (WCR), Current Ratio (CR), Return on Equity (ROE), Return on Assets (ROA), and Asset Turnover (AT). A Financial Sustainability Index (FSI) was constructed to classify companies. The results showed that WCR and CR were the most influential variables in explaining financial sustainability, while AT had the least impact. All variables demonstrated statistically significant relationships with the FSI. Moreover, machine learning models—particularly XGBoost and Random Forest—outperformed the traditional logistic regression model in predictive accuracy, with variations in variable importance rankings across models. The findings highlight the importance of focusing on working capital management and liquidity improvement to enhance financial sustainability, as well as the use of machine learning tools in financial forecasting to support more accurate strategic decision-making. This study contributes by providing a modern analytical framework to support the financial sustainability of industrial companies, with the potential for future application in other sectors. Specifically, machine learning models improved predictive accuracy by approximately 9.4% over the traditional logistic regression model, while SHAP-based analysis confirmed that WCR and CR carry the greatest weight in predicting financial sustainability. Accordingly, the study recommends that industrial companies prioritize working capital and liquidity management, that financial analysts and investors adopt machine learning models such as XGBoost and Random Forest in financial sustainability forecasting, that more comprehensive sustainability indices combining financial and operational performance be developed, and that decision-makers invest in training on machine learning tools and SHAP interpretation to support more reliable, evidence-based financial decisions.
Abstract
This study aimed to evaluate the financial sustainability of Iraqi industrial companies using machine learning models and to compare their performance with traditional statistical models. Five key financial variables were analyzed: Working Capital Ratio (WCR), Current Ratio (CR), Return on Equity (ROE), Return on Assets (ROA), and Asset Turnover (AT). A Financial Sustainability Index (FSI) was constructed to classify companies. The results showed that WCR and CR were the most influential variables in explaining financial sustainability, while AT had the least impact. All variables demonstrated statistically significant relationships with the FSI. Moreover, machine learning models—particularly XGBoost and Random Forest—outperformed the traditional logistic regression model in predictive accuracy, with variations in variable importance rankings across models. The findings highlight the importance of focusing on working capital management and liquidity improvement to enhance financial sustainability, as well as the use of machine learning tools in financial forecasting to support more accurate strategic decision-making. This study contributes by providing a modern analytical framework to support the financial sustainability of industrial companies, with the potential for future application in other sectors. Specifically, machine learning models improved predictive accuracy by approximately 9.4% over the traditional logistic regression model, while SHAP-based analysis confirmed that WCR and CR carry the greatest weight in predicting financial sustainability. Accordingly, the study recommends that industrial companies prioritize working capital and liquidity management, that financial analysts and investors adopt machine learning models such as XGBoost and Random Forest in financial sustainability forecasting, that more comprehensive sustainability indices combining financial and operational performance be developed, and that decision-makers invest in training on machine learning tools and SHAP interpretation to support more reliable, evidence-based financial decisions.