Bank capital buffers and lending in the euro area during the pandemic

Prepared by Cyril Couaillier, Marco Lo Duca, Alessio Reghezza, Costanza Rodriguez d’Acri and Alessandro Scopelliti

Published as part of the Financial Stability Review, November 2021.

Bank capital buffers are supposed to help banks to absorb losses while maintaining the provision of key financial services to the real economy in times of stress. Capital buffers that are usable along these lines should lessen the damaging effects that can arise from credit supply shortages. Making use of buffers entails using the capital space on top of regulatory buffers and minimum requirements and, in case of need, also using regulatory buffers. This special feature analyses bank lending behaviour during the pandemic to gain insights into banks’ propensity to use capital buffers and the impact of the regulatory capital relief measures implemented by the authorities. From a macro perspective, the euro area banking system as a whole was able to meet credit demand and withstand stress. However, this aggregate view reflects several factors, including the impact of extraordinary policy measures. A micro perspective thus can help to comprehend how the capital buffer framework and capital releases affected banks’ behaviour during the pandemic. The microeconometric analysis performed in this special feature shows that the banks that had limited capital space above regulatory buffers adjusted their balance sheets by reducing lending which could be interpreted as an attempt to defend capital ratios. This suggests that they were unwilling to use capital buffers. The results also show that the regulatory capital relief measures adopted during the pandemic, which added to banks’ existing capital space, were associated with higher credit supply. While more research is desirable, also on macro aspects, these findings suggests that more releasable capital could enhance macroprudential authorities’ ability to act countercyclically when a crisis occurs.

1 Introduction

A core goal of the Basel III capital buffer framework is to reduce the amplification effects of the banking system on the economic cycle. The framework envisages that bank capital is built up during periods when credit risk and financial vulnerabilities are increasing. Capital is then employed in case of need to absorb losses and meet credit demand during downturns and crises. Regulatory capital buffers sit on top of minimum capital requirements and constitute the combined buffer requirement (CBR).^[1] During downturns, banks can draw on the capital space above the CBR (i.e. management buffers or excess capital) and, in case of need, also the CBR itself, albeit with some limitations, notably the maximum distributable amount (MDA). When dipping into the CBR, banks must compute an MDA that caps the capital they can distribute, for example in the form of dividends, share buybacks or variable remuneration.^[2] In addition, to further support the financial intermediation capacity of banks, prudential authorities can release the countercyclical capital buffer (CCyB) or – dependent on the underlying risks – lower other regulatory buffers such as, for example, the systemic risk buffer (SyRB) in periods of distress, which should help to further facilitate the use of the underlying capital.

Concerns have been raised about whether some factors could impair the expected functioning of the framework. Specifically, in periods of economic or financial distress, banks may be unable to draw down the CBR if minimum requirements act as a binding constraint. Furthermore, banks may also be unwilling to dip into the CBR due to a number of factors.^[3] These include limitations to distributions that are triggered when capital ratios fall within the CBR^[4] and market pressure or stigma associated with the consumption of capital ratios. Ultimately, should impediments to the use of capital buffers affect a large portion of the banking system they can dampen aggregate lending supply to the real economy when most needed, thereby causing the banking system to behave procyclically and amplify a shock via credit supply shortages.

The pandemic offers some insights into the functioning of the capital framework, specifically banks’ propensity to use capital buffers and the impact of regulatory capital relief measures. Banks in the euro area entered the COVID-19 pandemic with relatively strong capital ratios, which were further supported by extraordinary policy measures throughout the pandemic.^[5] As a result, the euro area banking system as a whole was able to meet credit demand and withstand stress.^[6] Nevertheless, the behaviour of banks with little capital headroom above regulatory buffers (see Chart A.1) offers insights about the propensity of banks to use these buffers, and about the impact of the prudential capital releases which took place in early 2020.^[7]

2 Evidence on banks’ behaviour in the proximity of the combined buffer requirement

Differences in banks’ responses, depending on their distance to the CBR, provide a lens through which their willingness to use capital buffers can be assessed. A difference-in-differences analysis allows explicit testing of whether the lending behaviour of a selected group of banks, specifically those with a distance to the CBR smaller than 3 percentage points in the first quarter of 2020,^[8] differed significantly from that of banks with larger headroom above the CBR.^[9] Bank-level and loan-level data on the corporate loan books of a sample of euro area banks between the second quarter of 2019 and the fourth quarter of 2020 are employed to control for the heterogeneity of bank-specific characteristics and credit demand across firms.^[10] Additionally, information on the use of central bank funding (targeted longer-term refinancing operations or TLTROs) by banks and on whether individual loans are under payment moratoria or government guarantee schemes is used to isolate credit supply effects and control for the impact of policy support on lending.^[11]

Banks closer to their CBR were found to de-risk their balance sheet and curtail their lending to non-financial corporations (NFCs) more than other banks. Descriptive trends already suggest that banks closer to their CBR reduced their risk weight densities (defined as the ratio of risk-weighted assets (RWA) to total assets (TA)) more strongly during the pandemic than banks further away from it (see Chart A.1, panel b). The econometric analysis further shows that, during the pandemic, proximity to the CBR was associated with a 1.3 percentage point decline in risk weight densities relative to other banks, a material drop compared with an initial risk weight density of 35%. In addition, closer proximity to the CBR was related to lower lending to NFCs by a substantial 2.7 percentage points (see Table A.1). Overall, these results could provide a validation of the concern that banks are reluctant to dip into regulatory buffers.

Lower levels of lending by banks closer to their CBR resulted in greater credit constraints for non-financial firms reliant on these banks. In principle, the effect on individual firms of a reduction in credit supply from banks in the proximity of the CBR could be offset if other banks picked up the slack. In reality, however, firms which are heavily reliant on banks in the proximity of the CBR may struggle to replace existing sources of financing with alternative ones, or to establish new credit relationships, in turbulent times. Firm-level analysis provides evidence of these substitution impediments. Firms exposed to banks in the proximity of the CBR^[12] exhibited 5.3% lower borrowing after the onset of the pandemic than firms borrowing mostly from banks with larger capital buffers (see Chart A.2, panel a, left bar). In addition, borrowing from firms which, prior to the pandemic, had only a single relationship with a bank in the proximity of the CBR declined by an additional 1.7 percentage points after the onset of the pandemic (see Chart A.2, panel a, right bar).

In addition, government loan guarantees for NFCs alleviated some of the effects of weaker lending by banks closer to their CBR. Additional regressions^[13] show that new lending increases linearly as the distance to the CBR increases. Specifically, a 1 percentage point greater distance to the CBR yielded a 2.6% greater increase in unguaranteed new lending (see Chart A.2, panel b, dotted blue line). At the same time, the analysis shows that lending would have been lower without government loan guarantees and the loss in lending capacity would have been larger for banks closer to the CBR (see Chart A.2, panel b, dotted yellow line).^[14] This highlights the important role played by credit guarantee schemes in supporting firms’ liquidity needs and facilitating risk transfer.

3 Impact of regulatory capital relief measures on bank lending

The second part of the analysis investigates how regulatory capital relief measures affected credit supply.^[15] During the pandemic, the prudential authorities adopted these measures to support banks’ capacity to accommodate possible increases in risk weights and losses without curtailing lending.^[16] However, the size of the corresponding reduction in regulatory capital varied across banks because of the heterogeneity in existing capital buffers and the composition of capital.^[17]

The results show that regulatory capital relief measures had positive effects on lending, especially for banks closer to the CBR. A comparison of the credit trends suggests that – after the policy measures – banks benefiting from lower capital requirements expanded lending volumes more than other banks (see Chart A.3, panel a).^[18] A difference-in-differences analysis using firm-bank data on corporate loans to control for credit demand,^[19] and accounting for bank-specific characteristics and other concurrent policies, confirms these results.^[20] In particular, credit volumes increased by 3.1% after the regulatory capital relief measures, while interest rates on loans to firms eased by 7 basis points (see Chart A.3, panel b). Furthermore, the measures provided capital space to banks which were reluctant to use or get closer to the CBR, thereby supporting the credit supply from these banks (see Chart A.4, panel a).

Small and medium-sized enterprises benefited the most from the regulatory capital relief measures (see Chart A.4, panel b). The measures appear more effective for the provision of credit to those firms more reliant on bank lending, which have typically low or no access to debt securities funding and are thus less able to substitute across funding sources. Such a result is consistent with the objectives of the various policy actions undertaken during the pandemic.

4 Conclusions

The behaviour of individual banks during the pandemic offers some insights into the functioning of the Basel III capital buffer framework, in particular the usability of capital buffers and the impact of regulatory capital relief measures. First, the results show that proximity to the combined buffer requirement (CBR) is associated with contractionary balance sheet adjustments (i.e. lower lending to NFCs) to insulate capital ratios. This could indicate that banks in proximity of the CBR have been reluctant to dip into regulatory capital buffers. While from a macro perspective credit growth has been strong and the euro area banking system has been able to meet credit demand during the pandemic, the behaviour of banks with limited capital space above the CBR could indicate possible impediments to the smooth functioning of the capital framework in periods of economic distress. Second, this special feature finds that regulatory capital relief measures, which increased the capital space above the CBR, had positive effects on the supply of credit by individual banks. This supports the role of the reduction of regulatory capital buffers in mitigating the potentially procyclical behaviour of the banking system in periods of economic distress. From a policy perspective, those results could also suggest that more releasable capital would be desirable to enhance macroprudential authorities’ ability to act countercyclically when a crisis occurs and more banks approach the CBR, insofar as the stability of the system is not jeopardised. However, more research, on macro aspects, is desirable to further test and substantiate this hypothesis.