Accounting, Finance and Computational Intelligence

The digitalization of banking processes has significantly impacted financial performance and operational efficiency in banks. This study investigates the effects of digitalization on banks’ financial efficiency using a data-driven modeling approach. Financial data from 30 banks across different countries from 2012 to 2024 were collected and analyzed using dynamic panel models and Data Envelopment Analysis (DEA). The findings indicate that digitalization positively influences financial efficiency by enhancing data processing speed, reducing operational costs, and improving customer experience. Additionally, banks that leverage AI and machine learning in their financial processes exhibit superior performance compared to their counterparts. However, challenges such as high initial investment costs, cybersecurity risks, and organizational resistance to technological changes hinder full-scale adoption. This study provides strategic recommendations for policymakers and banking executives to optimize digitalization strategies.

In recent years, Robo-Advisors have emerged as effective tools for assisting individual investors in making optimal financial decisions. This study examines the impact of Robo-Advisors on individual investors' decision-making performance in Iran’s capital market. Data were collected through a randomized controlled trial (RCT) involving 200 individual investors, tracking their investment performance over a 12-month period. The results indicate that investors using Robo-Advisors made more rational decisions and achieved higher investment returns compared to their counterparts. Furthermore, financial experience and trust in technology played significant roles in the adoption and utilization of these systems. Challenges such as a lack of understanding of algorithm functionality and concerns about data security were identified as major barriers to adoption. This study provides recommendations for enhancing the acceptance and efficiency of Robo-Advisors in capital markets.

Deep learning-based financial forecasting models are increasingly used to analyze corporate profitability. This study investigates the impact of such models on profitability prediction accuracy compared to traditional methods. Financial data from 60 Tehran Stock Exchange-listed companies from 2015 to 2024 were collected and analyzed using deep learning models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Gradient Boosting models. The findings indicate that deep learning models outperform traditional regression and time series models in profitability prediction accuracy. Additionally, integrating deep learning models with dimensionality reduction techniques enhances performance. However, computational complexity, data volume requirements, and high processing costs remain major challenges in implementing these models in financial environments. This study provides recommendations for optimizing the use of deep learning in profitability forecasting.

Big data plays a crucial role in the financial decision-making of multinational corporations (MNCs). This study aims to analyze the impact of big data utilization on improving financial decision-making in MNCs. Financial and operational data from 50 multinational firms between 2015 and 2024 were collected and analyzed using dynamic panel regression models and time series analysis. Market volatility indices, return on investment, and financial efficiency were considered dependent variables. The findings suggest that big data enhances financial forecasting accuracy, improves resource allocation, and reduces macroeconomic decision-making risks. The role of AI-driven analytics in interpreting big data and optimizing financial processes was also evident. This study provides strategic recommendations for financial managers on maximizing big data’s potential.

Credit risk management is one of the most crucial challenges in the banking industry, which can be significantly enhanced through artificial intelligence (AI). This study examines the impact of AI on optimizing credit risk management processes in banks across Iran and Europe. A quantitative-experimental research approach was employed, collecting data on loan applications, credit scores, and customer repayments from 10 major banks in Iran and 10 European banks over the 2016–2024 period. Data Envelopment Analysis (DEA) and artificial neural networks were applied to assess the effectiveness of AI-driven credit scoring models. The findings indicate that banks utilizing AI-based credit assessment models achieve lower default rates and higher prediction accuracy compared to those relying on traditional methods. Moreover, significant differences between Iranian and European banks in AI adoption were observed, highlighting the influence of cultural, economic, and infrastructural factors on technology acceptance. This study provides policy recommendations for banking executives and regulators to enhance credit risk assessment models.

Accurate cash flow forecasting is one of the most critical challenges in financial management, as improvements in this area can lead to reduced financial risks and enhanced decision-making efficiency. In recent years, machine learning algorithms have emerged as effective tools for modeling and forecasting cash flows. This study employs a mixed-method approach. In the qualitative phase, semi-structured interviews with 25 financial managers of Tehran Stock Exchange-listed companies were conducted to identify key challenges and benefits of using machine learning in this domain. In the quantitative phase, financial data from 50 publicly traded firms from 2015 to 2024 were analyzed using linear regression, artificial neural networks, and boosting models such as XGBoost. The results indicate that machine learning algorithms outperform traditional models in cash flow forecasting accuracy. However, challenges such as algorithmic complexity, the need for large datasets, and issues related to model transparency hinder widespread adoption. This study provides recommendations for facilitating the implementation of machine learning in cash flow forecasting, offering valuable insights for financial managers and investors.

This study aims to examine the barriers to the adoption and implementation of blockchain-based financial reporting systems in financial organizations. This research was conducted using a qualitative approach with semi-structured interviews. A purposive sampling method was used, and 27 experts in finance, accounting, and information technology from organizations in Tehran participated in the study. Data collection continued until theoretical saturation was reached, and the data were analyzed using NVivo software and the qualitative content analysis method. The results indicated that adopting and implementing blockchain in financial reporting faces multiple organizational, technical, and regulatory barriers. At the organizational level, managerial and employee resistance to change and a lack of technical knowledge were the primary inhibitors. From a technical perspective, scalability limitations, incompatibility with legacy systems, and high implementation costs were identified as key challenges. At the regulatory level, a lack of legal clarity, ambiguity in legal responsibility, and concerns over data security and privacy emerged as significant obstacles. Despite these challenges, organizations recognize blockchain’s potential in enhancing transparency and efficiency in financial systems. To facilitate its adoption, it is recommended that clear legal frameworks be developed, investments in workforce training be increased, and IT infrastructures be improved to integrate blockchain with existing financial systems.

This study aimed to identify the barriers to developing automated financial reporting systems in organizations. This qualitative study employed a qualitative content analysis approach. Data were collected through semi-structured interviews with 22 financial and IT experts from organizations in Tehran. A purposive sampling method was used, and data collection continued until theoretical saturation was reached. The data were analyzed using open, axial, and selective coding in NVivo software. The results indicated that the barriers to developing automated financial reporting systems are categorized into four main areas: organizational barriers, technological barriers, financial barriers, and legal and regulatory barriers. Key barriers identified in this study included employee resistance to change, weak organizational culture, lack of senior management support, IT infrastructure issues, system integration complexities, security concerns, budget constraints, maintenance costs, and legal challenges related to data management. The findings suggest that successful development of automated financial reporting systems requires addressing organizational resistance, strengthening IT infrastructure, securing adequate financial resources, and establishing clear regulations. Strategic approaches in organizational culture, employee training, and senior management support can facilitate the adoption of these systems in organizations.