Commercial banks represent an important pillar of the national economy, serving as a tool for financing the economy and achieving growth. Their primary goal is to maximize profit by mediating between surplus and deficit units. This makes them a link that contributes to accelerating social and economic development by achieving their programs and objectives within a competitive banking environment. This, in turn, relies on making informed credit decisions. Granting credit is the primary function of any commercial bank, its primary source of income, and one of the most important services it provides to customers. The decision to grant credit also entails numerous financial problems that the bank can encounter due to risk, which is represented by customers' default, i.e., their inability to repay the loan amount and interest on time. Therefore, commercial banks have sought to establish systems and procedures to reduce or limit these risks and manage their credit activities within a permissible risk range. In order to reduce credit risks, banks rely on classical methods, but they sometimes lead to inaccurate decisions. Therefore, to make the credit granting decision typical, allowing for increased profitability without sacrificing security requirements, banks must apply modern methods to help classify sound and incapable institutions requesting loans and make rational and wise decisions. Therefore, the use of smart financial forecasting models represented by Kida model and Z-score model represents an important means of improving credit granting decisions. Hence, the current research came to shed light on the impact of using smart financial forecasting models on improving credit granting decisions in Iraqi commercial banks.

The Research Problem

The Iraqi environment is currently witnessing a phase of economic growth, encouraging investment, establishing projects, and encouraging small investors. In light of these changes, credit granting officials in commercial banks face new circumstances and variables in the credit granting environment, as the majority of borrowers are new colleagues at the bank and need funds to finance new projects. Intelligent financial forecasting models serve as an information system for measuring and communicating the results of financial events in institutions and businesses to their stakeholders. Therefore, banks are required to make informed and accurate credit decisions based on a thorough reading of the target environment. Based on this, the research problem was formulated in the main question: "What is the impact of using intelligent financial forecasting models on improving credit granting decisions in Iraqi commercial banks?" To achieve appropriate mechanisms to address this problem, the following sub-questions must be answered:

• What are the appropriate intelligent financial forecasting models through which Iraqi commercial banks can improve their internal operations?

• What are the appropriate mechanisms that Iraqi commercial banks can adopt to improve credit granting decisions? 3. What is the nature and type of relationship between intelligent financial forecasting models and credit granting decisions?

The Importance of the Research

The importance of the research is highlighted by its keeping pace with recent developments in the banking environment and its focus on the importance of improving credit granting decisions by relying on intelligent financial forecasting models. Hence, the importance of the research can be defined as follows:

• Providing an analysis of the level of credit granting decisions at Iraqi commercial banks, which contributes to building future information on the importance of these banks' annual reports.

• Directing the attention of relevant banks towards adopting intelligent financial forecasting models to improve the level of credit granting decisions.

• Building a positive perception of the importance of the models adopted in improving credit granting decisions, which contributes to making positive decisions and narrowing the research gap in this field.

• Directing commercial banks to adopt the proposed recommendations, which arise from addressing the internal problems facing commercial banks. This research is an essential part of addressing the problems of the banks studied.

Research Objectives

The primary objective of this research is to explore the impact of using intelligent financial forecasting models on improving credit granting decisions at a sample of Iraqi commercial banks, namely National Bank, Commercial Bank of Iraq, Mansour Bank, Bank of Baghdad, and Middle East Bank. The research also aims to achieve the following:

• Identify appropriate intelligent financial forecasting models through which Iraqi commercial banks can improve their internal operations.

• Identify appropriate mechanisms that Iraqi commercial banks can adopt to improve credit granting decisions.

• Determine the nature and type of relationship between intelligent financial forecasting models and credit granting decisions.

Hypothesis Development

The research is based on two hypotheses:

• There is a significant correlation between smart financial forecasting models and credit granting decisions.

• There is a significant impact of smart financial forecasting models on credit granting decisions.

Research Sample

The research community represents the banking sector of the Iraq Stock Exchange, while the research sample included five banks in the Iraq Stock Exchange for the fiscal period 2018-2022, National Bank, Commercial Bank of Iraq, Mansour Bank, Bank of Baghdad, and Middle East Bank.

Intelligent Financial Forecasting

Intelligent financial forecasting is based on the collection and analysis of a wide range of data, whether historical, such as prices, profits, cash flows, or influential economic and environmental data, to build models that learn from this data and predict future outcomes based on discovered patterns [1]. Intelligent financial forecasting is defined as the use of artificial intelligence and machine learning techniques to analyze financial data and predict the financial future of companies or markets [2]. It aims to provide accurate and rapid models that aid in financial decision-making, such as identifying market trends, assessing risks, and predicting future financial performance [3]. This concept is distinguished by its ability to handle large amounts of data and discover complex patterns and relationships that are difficult for traditional methods to detect, enhancing the accuracy of forecasts and increasing the effectiveness of financial planning [4]. Modern tools and techniques that use artificial intelligence and machine learning to analyze financial data and predict the financial future of companies or markets, such as intelligent financial forecasting models [5], are the result of intelligent financial forecasting models [5]. These are helpful in processing huge amounts of data and uncovering intricate patterns and relationships that might be challenging for traditional methods to notice [6]. By relying on techniques like neural networks, decision trees, and deep learning algorithms, intelligent financial forecasting models can provide more accurate forecasts that aid in the informed decision-making process for investors and financial managers [7]. Stock price estimation, risk assessment, and market trend prediction are accomplished through the use of these models, which reflect significant developments in financial analysis supported by digital technologies [8]. 

The Importance of Intelligent Financial Forecasting

Intelligent financial forecasting is depicted by Le et al. [9], Nayakv et al. [1]:

• The accuracy of its forecasting models is superior to those of traditional methods.

• The decision-making process is accelerated due to its speedy processing of large amounts of data.

• Market variables and economic developments can be adapted to models for their flexibility.

• Traditional financial analysis tools can be enhanced by integrating analytical tools and complementing their predictive capabilities.

In short, intelligent financial forecasting is an innovative development that enhances financial planning, decreases risks, and enhances chances of success in complex and constantly evolving financial markets.

Intelligent Financial Forecasting Models

Artificial Neural Network Models

Mimic the exertion of human neurons in data dispensation. They are used to predict financial variables such as profits, cash flows, or stock prices. They are used to forecast stock prices, analyze risks, and predict future profitability [10].

Machine Learning Models

These come in several types, including logistic regression and decision tree forecasting. They rely on historical data to identify patterns and are then used to predict future outcomes. They are also used to assess creditworthiness, predict corporate efficiency, and assess credit risk [11].

Time Series Models

Such as the ARIMA (statistical model) or Facebook's (Prophet) model, which deals with time-series data to predict future values ​​based on historical trends and patterns. They are used to forecast currency prices, stocks, and revenues on a monthly or quarterly basis [22].

The Kida Model

This is a statistical model primarily used in credit risk assessment. It aims to predict the likelihood of default or the risk associated with a particular customer. It can be used in credit granting decisions or in credit portfolio management [13].

The Z-score Model

This is one of the most popular models used in assessing the solvency and soundness of financial companies. It aims to predict the risk of bankruptcy or financial collapse of companies in the short and medium term [14].

Credit Granting Decisions

Credit granting decisions are defined as the actions taken by financial institutions (such as banks, finance companies, and financial institutions) to determine whether to provide credit facilities (loans, lines of credit, credit cards) to a specific beneficiary, for what term, at what interest rate, and under what other conditions [15]. These decisions are among the fundamental pillars of an organization's financial risk management [16], as they directly impact the company's overall profits and risks. They also ensure that financing is granted to individuals or companies that meet certain criteria in terms of repayment capacity, financial solvency, and compliance with the institution's credit policies [17]. Yang and Liu [18] pointed out that credit granting decisions are not merely random selections, but rather a systematic process based on careful risk analysis, specific criteria, and advanced assessment tools, with the goal of achieving a balance between investing in good customers and reducing risks to the institution [19]. This process contributes significantly to the sustainability of the banking sector and achieving the financial goals of institutions [20].

De Castro Vieira [21], Brotcke [22] and Pinandita [23] mentioned several elements and processes that contribute to the decision to grant credit, as follows:

• Creditworthiness assessment: This is done by analyzing the customer's ability to repay the debt. This is based on financial data, credit history, income, expenses, and previous obligations.

• Information gathering and data analysis: This includes the use of financial data (such as financial statements, account statements), credit data (credit history, payment history), and relevant personal or business information.

• Determining credit policies: This includes credit limits, acceptable risk ratios, pricing rates, and collateral requirements.

• Risk analysis: This involves assessing the likelihood of default using tools such as credit scoring models, risk assessment criteria, and scenario analysis.

• Final decision-making: This is based on the previous analysis and includes approval, rejection, or setting special conditions (such as increasing collateral or setting a specific credit ceiling).

To study the study's ability to predict intelligent financial performance using the Kida model for public joint-stock banks listed on the Iraq Stock Exchange, the researcher relied on the banks' annual financial reports published on the Iraq Stock Exchange for the period 2018-2022. The following are the data:

Bank Closing Price

The data indicate that investor interest in banks, as a sign of confidence, has generally increased with the rise in share prices over the years. The National Bank recorded the highest increase in interest, especially after 2018, with a sharp rise from 0.340 to 1.350, then a slight decline in 2022, reflecting fluctuations in investor confidence or expectations. Bank of Baghdad witnessed significant growth, especially after 2020, suggesting increased demand and possibly improved performance or market reputation.  The  results  of  the  Commercial  Bank  of  Iraq and Mansour Bank indicated relatively stable interest, but at lower rates. Middle East Bank has low interest, indicating weak confidence or limited investor targeting. Generally, high interest corresponds to a high share price and reflects varying expectations and confidence in the performance of different banks over the years.

Table 1: Closing price ranking of the studied banks

Table 2: Financial Forecasting Using Z-score

The value of the Kida model

Bank of Baghdad shows a clear interest and greater growth compared to other banks, with a value of 0.199, indicating a greater response to economic growth or market conditions. Meanwhile, National Bank, Mansour Bank, Commercial Bank of Iraq, and Middle East Bank showed less interest, with values ​​between 0.069 and 0.103, indicating a weaker response to growth or less bias towards economic changes. This disparity reflects the banks' different strategies, their level of interaction with the market, or the extent of their reliance on economic growth in their operations. In general, Bank of Baghdad demonstrates greater flexibility and responsiveness to growth variables, while other banks remain less reactive, reflecting different approaches and strategies in asset and risk management.

Z-score Model

The model was applied to commercial banks listed on the Iraq Stock Exchange. The following is the model equation:

Z=1.2X1+1.4X2+3.3X3+0.6X4+0.999X5

X1: Working capital to total assets.

X2: Retained earnings to total assets.

X3: Earnings before interest and taxes to total assets.

X4: Market value of shareholders' equity to total liabilities.

X5: Sales to total assets.

The absolute numbers in the equation represent the discrimination coefficient for each variable and are constant for each variable.

The higher the value of Z, the more reliable the joint-stock company's financial position is, while a lower value indicates the likelihood of financial failure. The following table shows the Z values ​​for the commercial banks in the study sample:

• The National Bank's Z-score was 0.88, which is less than 1.81, and therefore the bank can be judged to be at risk of financial failure.

• The Commercial Bank of Iraq's Z-score was 6.052, which is greater than 2.99, indicating that the bank is capable of continuing.

• The Mansour Bank's Z-score was 2.735, which is between 1.81 and 2.99, indicating that it is difficult to predict the bank's future, as it falls into the gray (unclear) zone.

• The Bank of Baghdad's Z-score was 28.11, which is a high percentage and indicates that this bank is capable of survival and continuity. Its Z-score is much higher than the standard of 2.99, and is the highest among other banks, indicating the strength of its financial position. 

The Z value for the Midpoint East Bank accomplished 26.18, which is a high percentage and point out that this bank is able to survive and carry on, as the Z value for this bank is much higher than the standard of 2.99, and this specify the vigour of its financial place and effective administration.

The accuracy of customer risk assessments is improved by intelligent financial forecasting models, which reduces the likelihood of unsecured or non-repayable loans.

• Immediate and reliable results are provided by forecasting tools, which speeds up the loan approval process and improves banking operations efficiency.

• The stability of the banking sector and financial losses can be improved by utilizing intelligent models to decrease defaults and insolvency.

• Models enable banks to take proactive preventative measures by predicting changes in market and economic conditions.

• The models' results can be incorporated into banks' credit policies to reflect economic realities and future expectations.

• Banks can maximize the efficient use of capital by utilizing accurate risk assessments to determine credit allocation and reduce risk reserves.

• By employing intelligent models, credit granting processes become more transparent, boosting the confidence of both customers and investors.

• Adapting smart models to Iraq's unique economic environment requires significant investment in technology and training, and presents challenges.

Recommendations

• To build accurate and reliable predictive models, banks need to allocate resources to modernize their technological infrastructure and collect high-quality data.

• Training employees to use smart models and understand their results effectively is crucial for making informed and informed decisions.

• A comprehensive evaluation framework must incorporate smart models along with traditional financial analysis and external economic benchmarks.

• The accuracy of results and their relevance to local market conditions must be ensured by designing models that are tailored to Iraq's economic and social characteristics.

• In order to create a culture of technology adoption, encourage the adoption of artificial intelligence and data analysis tools in all banking departments.

• Create regulations and legislation to guarantee that models are used responsibly and transparently, while also taking into account data protection and customer rights.

• To guarantee their continued effectiveness, review model performance periodically and update them based on new data and economic changes.

• Developing advanced models that incorporate recent developments in the field of financial forecasting and artificial intelligence by forming partnerships with universities and research institutions.

1. Nayak, S.C. Forn et al. "Intelligent Financial Forecasting with an Improved Chemical Reaction Optimization Algorithm Based Dendritic Neuron Model." IEEE Access, vol. 10, 2022, pp. 130921–130943.

2. Banica, L. Forn et al. "Intelligent Financial Forecasting, the Key for a Successful Management." International Journal of Academic Research in Accounting, Finance and Management Sciences, vol. 2, no. 3, 2012, pp. 192–206.

3. Ibrokhim, I. Forn et al. "Intelligent Financial Forecasting: A Fusion of Computer Engineering and AI in Accounting." 2024 International Conference on IoT, Communication and Automation Technology (ICICAT), IEEE, 2024, pp. 310–315.

4. Pamisetty, V. "Intelligent Financial Governance: The Role of AI and Machine Learning in Enhancing Fiscal Impact Analysis and Budget Forecasting for Government Entities." SSRN, 2023, SSRN 5159909.

5. Niu, T. Forn et al. "Developing a Deep Learning Framework with Two-Stage Feature Selection for Multivariate Financial Time Series Forecasting." Expert Systems with Applications, vol. 148, 2020, p. 113237.

6. Prasad, G.V. Forn et al. "Financial Time Series Forecasting Using Hybrid Evolutionary Extreme Learning." Proceedings of World Conference on Artificial Intelligence: Advances and Applications: WCAIAA 2024, Springer Nature, 2024, p. 93.

7. Wen, Y. "Research and Design of ERP System for Small and Medium-Sized Enterprises under Great Intelligence Mobile Cloud." IOP Conference Series: Materials Science and Engineering, vol. 646, no. 1, 2019, p. 012036.

8. Williams, D. "Multimodal Deep Learning Frameworks for Financial Sentiment Analysis and Price Prediction." 2024.

9. Le, D.Y.N. Forn et al. "Analysing Stock Market Trend Prediction Using Machine & Deep Learning Models: A Comprehensive Review." 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), IEEE, 2020, pp. 1–10.

10. Dongare, A.D. Forn et al. "Introduction to Artificial Neural Network." International Journal of Engineering and Innovative Technology (IJEIT), vol. 2, no. 1, 2012, pp. 189–194.

11. Sullivan, E. "Understanding from Machine Learning Models." The British Journal for the Philosophy of Science, 2022.

12. Liu, M. Forn et al. "Scinet: Time Series Modeling and Forecasting with Sample Convolution and Interaction." Advances in Neural Information Processing Systems, vol. 35, 2022, pp. 5816–5828.

13. El Bachir, M.M. Forn et al. "Predicting Financial Failure in Algerian Public Insurance Companies Using the Kida Model." Journal of Applied Data Sciences, vol. 5, no. 2, 2024, pp. 508–519.

14. Zhu, L. Forn et al. "Financial Risk Evaluation Z-Score Model for Intelligent IoT-Based Enterprises." Information Processing & Management, vol. 58, no. 6, 2021, p. 102692.

15. García, V. Forn et al. "Synergetic Application of Multi-Criteria Decision-Making Models to Credit Granting Decision Problems." Applied Sciences, vol. 9, no. 23, 2019, p. 5052.

16. Palazuelos, E. Forn et al. "Auditing and Credit Granting to SMEs: An Integrative Perceptual Model." Managerial Auditing Journal, vol. 35, no. 1, 2020, pp. 152–174.

17. Cardoso, D.D. Forn et al. "Risk Assessment When Granting Credit to Non-Financial Legal Entities." Revista Ambiente Contábil, vol. 16, no. 2, 2024.

18. Yang, Y.C. Forn et al. "Determinants of Banking Sector’s Credit Granting Policy for the Yacht Industry in Taiwan." Maritime Business Review, vol. 1, no. 1, 2016, pp. 55–75.

19. Lipshitz, R. Forn et al. "Intuition and Emotion in Bank Loan Officers' Credit Decisions." Journal of Cognitive Engineering and Decision Making, vol. 1, no. 2, 2007, pp. 212–233.

20. Saliya, C.A. "Dynamics of Credit Decision-Making: A Taxonomy and a Typological Matrix." Review of Behavioral Finance, vol. 12, no. 4, 2020, pp. 357–374.

21. de Castro Vieira, J.R. Forn et al. "Towards Fair AI: Mitigating Bias in Credit Decisions—A Systematic Literature Review." Journal of Risk and Financial Management, vol. 18, no. 5, 2025, p. 228.

22. Brotcke, L. "Time to Assess Bias in Machine Learning Models for Credit Decisions." Journal of Risk and Financial Management, vol. 15, no. 4, 2022, p. 165.

23. Pinandita, D.S. Forn et al. "Factors in Credit Decision-Making and Related Research Gaps in Indonesia: A Literature Review." 2022 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), IEEE, 2022, pp. 0117–0121.

24.