دانلود مقاله تحقیق عملیاتی و روش های هوش مصنوعی در بانکداری
چکیده
1. مقدمه
2. نقش حیاتی تکنیک های OR و AI در بانکداری
3. روش شناسی
4. موضوعاتی برای روش های OR و AI در تحقیقات بانکی
5. تکنیک های OR و AI در تحقیقات بانکی
6. دستورالعمل برای تحقیقات آینده
7. نتیجه گیری
ضمیمه. مواد تکمیلی
منابع
Abstract
1. Introduction
2. The crucial role of OR and AI techniques in banking
3. Methodologies
4. Topics for OR and AI methods in banking research
5. OR and AI techniques in banking research
6. Directions for future research
7. Conclusion
Appendix. Supplementary materials
References
چکیده
بانکداری یک موضوع محبوب برای تحقیقات تجربی و روش‌شناختی است که از روش‌های تحقیق عملیاتی (OR) و هوش مصنوعی (AI) استفاده می‌کند. این مقاله یک بررسی کتابشناختی جامع و ساختار یافته از تحقیقات مبتنی بر OR و AI ارائه می‌کند که در دهه گذشته به صنعت بانکداری اختصاص یافته است. این مقاله به بررسی موضوعات اصلی این تحقیق از جمله کارایی بانک، ارزیابی ریسک، عملکرد بانک، ادغام و ادغام، مقررات بانکی، مطالعات مرتبط با مشتری و فین‌تک در صنعت بانکداری می‌پردازد. نتایج نظرسنجی بینش جامعی را در مورد مشارکت روش‌های OR و AI در بانکداری ارائه می‌کند. در نهایت، ما چندین جهت تحقیقاتی را برای مطالعات آتی پیشنهاد می‌کنیم که شامل موضوعات و روش‌های نوظهور بر اساس نتایج نظرسنجی است.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Banking is a popular topic for empirical and methodological research that applies operational research (OR) and artificial intelligence (AI) methods. This article provides a comprehensive and structured bibliographic survey of OR- and AI-based research devoted to the banking industry over the last decade. The article reviews the main topics of this research, including bank efficiency, risk assessment, bank performance, mergers and acquisitions, banking regulation, customer-related studies, and fintech in the banking industry. The survey results provide comprehensive insights into the contributions of OR and AI methods to banking. Finally, we propose several research directions for future studies that include emerging topics and methods based on the survey results.
Introduction
The assessment of various financial aspects of banks occupies an essential place in the academic literature because of the crucial intermediation role of the banking industry in financial markets (Ioannidis et al., 2010; Tzeremes, 2015; Zopounidis et al., 2015). Along with an increasing need to use more sophisticated methods in banking research, several studies in this area employ operational research (OR) and artificial intelligence (AI) methods. Thus, the existing literature examines some fundamental research questions in banking research using OR and AI techniques, such as addressing the fairness issue in banking performance evaluation (Chen et al., 2020) and increasing the accuracy of the prediction of default risk and bank failure (Boussemart et al., 2019), as well as helping centralized organizations (e.g., headquarters of banks) to incentivize their units (i.e., bank branches) and optimize their performance (Afsharian et al., 2019). A rising trend in the utilization of OR and AI techniques to address banking challenges indicates their increasing importance and relevance for this field (Akkoç, 2012; Manthoulis et al., 2020; Yao et al., 2017).
Conclusion
This article presented an extensive review of the crucial role played by OR and AI methods in banking research by analyzing a total of 338 studies published between 2010 and 2020. We described six general topics that employ OR and AI methods to address various crucial banking issues: banking efficiency, risk management, bank performance, banking regulation, M&A, customer-based studies, and fintech in the banking industry. We also outlined the most widely used OR methods, including DEA, ABM, MC, fuzzy logic, and AI techniques, including SVMs, NNs, and ensemble methods. This article contributes to the literature by complementing the prior bibliographic surveys, covering various general banking topics, and summarizing the different methods applied.
We also suggested potential future research directions from both topic and methodology perspectives. Researchers could explore and verify various OR and AI methods in banking studies from a methodological perspective. Thus, regarding future research topics, efficiency forecasting related to the evaluation of financial stability could justify further exploration, as could the investigation of non-financial risks, such as conducting risks, which has received very limited attention in the academic literature to date. Future studies might also explore the impacts of government regulations and managerial behaviors on risk-taking by banks. Finally, future research could also apply other AI methods (e.g., unsupervised machine learning) or fresh combinations of OR and AI techniques to banking research.