资源描述
To supervise ortoselfsupervise: amachine learning based comparison oncredit supervision Jos Amrico Pereira Antunes * Introduction e need for banking supervision is the result of a chain of events triggered by the mar- ket failure that results in the nancial system itself. Informational asymmetry between economic units makes the allocation of resources inecient without a hub to connect them. Hence, nancial intermediary is the prerequisite for nancial intermediation. Overcoming the rst market failure gives rise to the second one: principalagent prob- lem. Intermediating means capturing someone elses deposits and directing it to a third party at the intermediarys will. From the depositors perspective, the sounder the bank, the safer the deposits. However, this may not be the case from the perspective of the management, who can decide for a riskier, thus protable, path. is environment can impede the alignment of interests between depositors and management, making nan- cial intermediation inecient without the presence of an independent external agent, namely, banking supervision, which asserts the solvency of intermediaries. Abstract This study investigates the need for credit supervision as conducted by on-site banking supervisors. It builds on a real bank on-site credit examination to compare the perfor- mance of a hypothetical self-supervision approach, in which banks themselves assess their loan portfolios without external intervention, with the on-site banking supervision approach of the Central Bank of Brazil. The experiment develops two machine learn- ing classication models: the rst model is based on good and bad ratings informed by banks, and the second model is based on past on-site credit portfolio examinations conducted by banking supervision. The ndings show that the overall performance of the on-site supervision approach is consistently higher than the performance of the self-supervision approach, justifying the need for on-site credit portfolio examination as conducted by the Central Bank. Keywords: Bank supervision, Machine learning, Loan loss provisions, On-site credit supervision JEL Classication: C45, G21, G28, M48 Open Access The Author(s), 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the articles Creative Commons licence, unless indicated otherwise in a credit line to the mate- rial. If material is not included in the articles Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit cr eat iv eco mmons . or g/ licen ses/ b y/4. 0/. RESEARCH Antunes Financ Innov doi/10.1186/s40854021002424 Financial Innovation *Correspondence: jose.antunesbcb.gov.br Central Bank of Brazil, Av Presidente Vargas, 730, Rio de Janeiro 20231-044, BrazilPage 2 of 21 Antunes Financ Innov e purpose of banking supervision is to keep the nancial system sound and safe, ensuring that the nancial regulation, the set of rules governing the nancial system, is followed (Masciandaro and Quintyn 2015). 1 e agship of nancial regulation is the Basel Accords, which are the policy directives prepared by the Basel Committee on Banking Supervision, a high-level committee of the Bank of International Settlements (BIS). Moreover, this nancial regulation is adopted worldwide. e third Basel Accord, which emerged in the aftermath of the Great Financial Crisis (2008/2009), broadened the scope of prudential regulation and embraced liquidity and leverage as relevant microprudential issues. However, the solvency-based perspective remains the focus of prudential regulation, highlighting the capital adequacy ratio as its leading indicator. From the solvency perspective, keeping the nancial system sound and safe means asserting the worth of the banks assets (Hellwig 2014). In particular, credit portfolio assessment, due to its relevance among assets, is an important task assigned to banking supervision. From the accounting standpoint, the credit portfolio is often measured by amortized cost deduced from the loan loss provision. e loan loss provision is a com- bination of incurred and expected losses, which is designed to adjust the credit portfolio to its fair value. e role of banking supervision is to assess loan portfolios and check whether banks comply with rules and regulatory requirements, especially the adequacy of loan loss provision to the loan portfolio risk prole. Although credit portfolio assessment is a classic banking supervision predicate, the Great Financial Crisis slowed down a self-regulation process that gradually increased the reach of internal-based models. e internal ratings-based approach, an important innovation introduced in the Second Basel Accord, allows banks to replace regulatory standardized models with proprietary versions internally developed. Continuous inno- vation in the nancial system, brought about by the technology revolution, may suggest the reignition of this process in the spirit of Stefanadis (2003). De Chiara etal. (2018) analyzed the eect of tighter regulation and powerful supervision in the nancial sec- tor and the consequent social costs. e authors argued that the optimal supervisory architecture combines a supervisory regime where direct assessment by a supervisor is always required (mandatory supervision) with a exible supervision regime where banks self-select the regulatory contract designed for their level of risk. In this sense, this study investigates the need for credit supervision as conducted by the Central Bank of Brazil (CBB). It builds on a real bank on-site credit examination to compare the performance of a hypothetical self-supervision approach, where banks themselves assess their loan portfolios without external intervention, with CBBs on-site banking supervision. To conduct this experiment, we train two machine learning clas- sication models: (1) a model based on good and bad ratings informed by banks and (2) a model based on past on-site loan portfolio examinations conducted by CBBs banking supervision. 1 Although complementary, banking regulations and banking supervision are separate activities, usually performed by dierent actors. e former concerns the rules governing the nancial system, whereas the latter regards the enforce- ment of such rules (Masciandaro and Quintyn 2015). In the Brazilian nancial system, the National Monetary Council is responsible for banking regulations and the Central Bank of Brazil (CBB) is responsible for banking supervisionPage 3 of 21 Antunes Financ Innov e ndings show that CBBs on-site supervision consistently outperforms the self- supervision approach, which justies the necessity of on-site credit portfolio examina- tion as conducted by CBB. e remainder of this paper is structured as follows. Section2 discusses the related literature on nancial supervision and loan loss provisioning. Section3 highlights the Brazilian nancial system, credit regulation, and supervision. Section 4 presents the empirical analysis comprising (1) the machine learning algorithm used to develop classication models based on on-site supervision and banks experience; (2) on-site examination procedure that produced the ground truth against which both supervisory approaches are compared; and (3) the analysis of the results. Section 5 concludes the paper. Banking supervision andloan loss provisioning regulation e nancial crisis casted doubts over policy certainties ranging from monetary policy to nancial regulation and supervision. Barth etal. (2013) and Blanchard (2009) argued that the crisis was the result not only of incomplete regulation but also of ineective supervision. Bernanke (2010) ascertained that stronger regulation and supervision aimed at problems with underwriting practices and lenders risk management would have been a more eective and surgical approach to constraining the housing bubble than a general increase in interest rates. eir assertion is based on evidence of declining lending standards during the boom. Vials etal. (2010) drew lessons from the nancial crisis to answer why countries with similar nancial systems, operating under the same set of global rules, were less aected than others. e authors argued that, besides the need for better regulations in areas such as capital, liquidity, provisioning, and others, nancial supervision was not eective as it should have been. Moreover, they mentioned that to be eective, nancial super- vision must be intrusive, adaptive, skeptical, proactive, comprehensive, and conclusive. erefore, a twofold approach was needed. On the one hand, the regulation was broad- ened and enhanced, including the explicit nancial stability mandate, headed by nan- cial stability committees. On the other hand, supervisory skills incorporated additional toolkits to face the forward-looking assessments of risks and the challenging macropru- dential dimension the crisis added to supervision. Masciandaro and Quintyn (2013) stated that nancial supervision is the vital link between nancial regulation and nancial sector stability. Financial supervision acts as an essential complement to nancial regulation in the authorities pursuit of nancial stability. e importance of nancial supervision as an independent policy area moti- vated the development of strands in the literature to understand its role. Among the topics that gained attention are as follows: the relationship between the supervision and monetary policy (Goodhart and Schoenmaker 1995; Poloz 2015; Antunes, Moraes and Montes 2016); supervisory architecture (Taylor 1995, 1996); and supervisory governance (Kane 1989; Randall 1993). Establishing clearly the roles assigned to nancial regulation and supervision is a start- ing point to Freixas and Santomeros (2002) thorough review of the theoretical frame- work of banking regulation and supervision. On the one hand, nancial intermediaries present the solution to market imperfections derived from asymmetric informationPage 4 of 21 Antunes Financ Innov problems. On the other hand, regulation and supervision are the response to avoid exces- sive risk-taking or undesired monopolistic powers that can emerge as consequences of nancial intermediaries actions. Whenever a nancial intermediary addresses a mar- ket failure, it works as a second-best solution, for it causes another market failure and requires nancial regulation and supervision. Among the market failures addressed by nancial intermediaries, such as providing liquidity risk insurance, creating safe assets, screening of potential borrowers, and moni- toring customers actions and eorts (Freixas and Santomero 2002), we draw attention to the screening and monitoring activities as those directly linked to this study. e quality of banks assets, as well as the quality of their balance sheets, points to the quality of screening and monitoring activities. Gorton (1988) argued that a bank failure may signal both a weakness limited to the bank and fragility in the system as a whole. us, the systemic risk may emerge from microprudential failures that make depositors question the soundness of the nancial system. Financial supervision is entitled to assess the quality of screening and monitoring practices. Moreover, for credit, it is responsible to spot bad credit clusters and properly resolve them before they turn into a going-con- cern problem. Such action avoids spillover eects and mitigates systemic risk. An extensive number of studies have considered the inuence of nancial supervision on banks risk-taking to be relevant. However, results are mixed when it comes to the eects of supervision on nancial stability. For instance, Bhattacharya etal. (2002) con- cluded that intense supervision can improve the timeliness of supervisory intervention, whereas Delis and Staikouras (2009) showed that intense supervision can limit banks risk-taking. White (2006) defended supervision and regulation as the best instruments to achieve nancial stability, whereas Barth etal. (2004, 2008, 2013) argued that the e- ciency of nancial intermediation, hence nancial performance, is reduced by nancial supervision. Meanwhile, Brown and Din (2011) used a competing risk hazard model for bank survival to study bank failures in 21 emerging market countries in the 1990s and show that a government is less likely to take over or close a failing bank if the bank- ing system is weak, hence establishing a Too-Many-to-Fail eect based on regulatory forbearance. Brazilian nancial system: credit regulation andsupervision In the Brazilian nancial system, henceforth nancial system, dierent types of nan- cial institutions coexist, ranging from niche institutions, which explore specic types of activities, to universal banks, which gather many dierent activities in the same entity. e nancial system is complex and well developed. In June/2019, it comprises 178 banks, mounting to 126% of GDP in assets, and 47% of GDP in credit, 2 which makes Brazil an interesting case study. National Monetary Council (NMC) is the nancial regu- lator, and dierently from other jurisdictions, CBB is responsible for all aspects regard- ing nancial institutions oversight, from entry to the resolution, concordantly with Barth etal. s (2004) public interest view. 2 Data collected from the CBB website nancial series repository: h t t p s :/ w w w3. b cb. g ov . br/ if da t aPage 5 of 21 Antunes Financ Innov In Brazil, the supervisory process partially follows the Twin Peaks model (Group of irty 2008; FSI 2018), which recommends supervisory specialization by objectives: prudential monitoring of regulated institutions and oversight of business conduct. Although the Twin Peaks model expects two separate nancial supervision authorities to tackle banking supervision, the Brazilian solution is a hybrid model in which an inte- grated supervisor, namely, CBB, holds both objectives inside the same authority. e prudential regulation (henceforth banking supervision) is the focus of our analy- sis. e objective of banking supervision is to assess the soundness of nancial institu- tions, mainly commercial banks, and to assert that regulation is complied. It consists of two cornerstones: examination, or on-site supervision, and monitoring, or o-site supervision. On-site supervision follows a supervision cycle and involves sending super- visory sta to banks to conduct specic examinations. O-site supervision is a perma- nent process that analyzes banks performance and compliance to regulation based on multiple sources of data, as
展开阅读全文