Prospects for euro area bank lending margins in an extended low-for-longer interest rate environment

Prepared by Ugo Albertazzi, Desislava Andreeva, Marco Belloni, Alberto Grassi, Christian Gross, Jonas Mosthaf and Tamarah Shakir

Published as part of the Financial Stability Review, November 2020.

In the wake of the pandemic, the economic outlook has deteriorated, the recovery is uncertain and interest rates are expected to remain at historical lows for even longer. The persistently low interest rate environment can both support and dampen the profitability and resilience of euro area banks. This special feature examines some aspects of how the low-for-even-longer interest rate environment may affect bank lending margins, and in turn banks’ ability to lend to the real economy and overall financial stability. It analyses euro area banks from 2000 onwards and finds evidence that margins fall more in response to declines in nominal short-term rates when these are low to begin with. The compression of margins reflects the sluggish response to further policy rate cuts of deposit rates as they approach the zero lower bound. Moreover, the analysis indicates that bank margins and overall profitability are influenced by both the level of real rates and, more materially, the level of inflation expectations embedded in nominal rates, which reflects the fact that bank profits are partly akin to seigniorage. Should a large share of deposit rates continue exhibiting persistent downward rigidity in the absence of a rebound in inflation expectations, the outlook for net interest margins will remain weak, adding to the bank balance sheet stress induced by the pandemic, notwithstanding the mitigating effect of low interest rates on bank provisions.

1 Introduction

The low interest rate environment has featured heavily in debates on prospects for the euro area banking system, which faces persistently weak profitability.^[1] In particular, there has been an ongoing debate about the extent to which low and negative interest rates may, over time, become a drag on bank profitability and a cause of higher risk-taking by banks – possibly increasing risks to euro area financial stability. The debate reflects the fact that while euro area banks’ return on equity has increased from its trough of less than -3% in 2011-12, it has struggled to rise above 6% on average, which is below estimates of the cost of equity and low in comparison to other jurisdictions. At the same time, as set out in previous issues of the FSR, in recent years there have been growing signs of increased risk-taking, such as expanding mortgage lending and consumer credit at weaker terms and conditions in some countries. That said, overall bank risk-taking was not judged to be particularly elevated, especially given the better capitalisation of banks since the crises earlier in the decade.

In the wake of the pandemic, the low interest rate environment is expected to persist even longer, driven by lower real interest rates. Very low nominal interest rates have been a feature of the economic environment across advanced economies since 2009. They reflect a decline in equilibrium interest rates, i.e. the real short-term interest rates which would prevail if economies operated at their productive capacity (see Chart B.1), as well as policy rate cuts and additional measures introduced by central banks to stabilise macroeconomic activity and safeguard their price stability objectives in the course of the last decade. In parallel, longer-term interest rates have also declined to such an extent that, as at late September 2020, risk-free rates with a maturity as long as 20 years were below zero (see Chart B.1, right panel). Some financial market participants now only see short-term money market rates becoming positive again from 2030, around five years later than anticipated in late 2019 (see Chart B.1, left panel, right-hand graph).

This special feature examines some aspects of how the new context may affect banks’ net interest income. The first section focuses specifically on the impact of the real versus the nominal component of interest rates on net interest margins, returns and loan loss provisions. It also investigates whether the adverse impact of falling interest rates on net interest margins worsens when nominal short-term rates are negative and when low rates persist for an extended period. Taken together, these findings shed light on the potential impact of the low-for-longer interest rate environment on banks’ profitability. Of course, these effects can vary by bank, and by business line or portfolio (see Box A). Given the finding of non-linearity around negative interest rates, the second section discusses the prospects for overcoming the zero lower bound on customer deposit rates.

2 The role of real and nominal rates in bank intermediation

The real rate component of interest rates may affect bank profitability separately from changes in inflation expectations. Nominal interest rates consist of two components: the real interest rate and compensation for the loss of purchasing power over the life of a contract, which reflects the prevailing inflation expectations.^[2] An increase in real rates, especially long-term interest rates, tends to mirror a strengthening in the expected growth of the real economy. Alternatively, it may capture changes in the creditworthiness of bank borrowers, which tends to worsen if real debt servicing costs increase and result in higher credit risk premia embedded in bank lending rates. By contrast, an increase in inflation expectations may lead to higher margins because part of banks’ funding (i.e. deposits held for transaction purposes) is remunerated at zero rates, or at rates that only partly reflect prevailing financial market conditions, while lending rates include a premium for higher expected inflation.

The current interest rate configuration appears largely to reflect lower real rates, in the context of secular stagnation and now the impact of the pandemic.^[3] The economic literature identifies a number of structural factors exerting downward pressure on real interest rates. Of these, demographic developments, a slower pace of technological innovation, rising inequality and regulatory changes which create additional demand for safe and liquid assets have been highlighted in the debate. The pandemic has led to weaker aggregate demand and consumer and business confidence indicators. In turn, this has weighed on bank profits via lower intermediation volumes and deteriorated borrower creditworthiness, as reflected in costs associated with loan losses. Moreover, productivity may also be persistently lower, serving to reduce real interest rates further.

An updated analysis of euro area banks confirms that higher nominal short-term interest rates and a steeper yield curve support banks’ net interest margins (see column (1) of Table B.1).^[4] The core element of bank intermediation is the ability to “borrow short” and “lend long” ‒ in other words, banks fund longer-term assets (e.g. mortgages) with shorter-term liabilities (e.g. customer deposit accounts, some of which offer transaction services and are not remunerated). They take a margin from the difference in interest rates typically implied by this maturity transformation.^[5] Even outside of a low interest rate environment, these intermediation margins increase when interest rates are higher. This is because the rates that banks earn on the longer-term assets rise, while the part of banks’ funding costs formed by deposits generally tends to respond less.^[6]

Notably, higher nominal interest rates driven by variation in inflation expectations are found to be particularly important for margins.^[7] The explicit distinction between changes in nominal interest rates due to variation in real rates and changes driven by higher inflation expectations is a key feature of this analysis. Higher interest rates when driven by higher inflation expectations are found to lead to a significant increase in net interest margins. Generally, this suggests that part of bank profitability is akin to seigniorage. That is to say, banks earn returns from having access to non-interest-bearing funding (customer deposits), while their assets generate returns which compensate for the anticipated loss of purchasing power due to inflation. Interestingly, higher current inflation rates can only marginally boost nominal profitability, presumably because unanticipated changes in inflation cannot be incorporated into the pricing of financial contracts. The above effect is also visible when expressing margins in real terms and also carries over to overall profitability (for both return on assets (ROA) and return on equity (ROE)).

When higher rates reflect real factors, the impact on profitability is found to be more mixed. Higher real long-term interest rates for a given level of inflation expectations tend to be associated with slightly lower net interest income.^[8] Higher real short-term rates support banks’ margins, reflecting the limited sensitivity of remuneration on transaction deposits to market conditions.

Lower nominal short-term interest rates squeeze margins more when short-term rates are low. The results from including a quadratic term of the nominal short-term interest rate in the specification show that low starting values for interest rates result in nominal short-term rates having a steeper impact on banks’ net interest margins (see Chart B.2, left panel).^[9] Adding an interaction term between the short-term interest rates and a dummy for the period over which negative interest rates on excess reserves held in the ECB’s deposit facility have been applicable reveals that the impact of nominal short-term interest rates on the net interest margin increases by a factor of 10 when short-term rates are negative compared with a positive starting point. This is also consistent with there being a zero lower bound on the interest rates for retail deposits.

The impact of low interest rates on bank profitability may change over time, but in principle the effect of longevity can operate in both directions. On the one hand, banks’ intermediation capacity can be damaged by long-lasting low profitability; on the other hand, banks may only start adjusting their business model to match the environment (e.g. by passing on negative interest rates to depositors) if they expect this environment to last. Time dummies to incorporate the persistence of low interest rate periods^[10] over the years reveal a notable deterioration in the NIM in the fifth year, followed by a stabilisation (see Chart B.2, right panel). The results above do not control for possible transition effects, which may originate from the gradual repricing of assets and liabilities and may be expected to temporarily mitigate the adverse impact of lower rates on bank margins. Controlling for that, which would require detailed information on the financial duration of both assets and liabilities, could lead to a less benign assessment of the role of persistently low rates.

3 Prospects for the pass-through of negative interest rates to deposit rates

Since 2014 euro area banks have only gradually moved to charging negative interest rates on customer deposits. The stock of retail deposits priced at negative rates has gradually increased over the last six years, reaching about one-third of all corporate deposits while remaining considerably more contained for household deposits. Despite this, deposits stuck at the zero lower bound now represent the bulk of total retail deposits (for instance, the share of retail deposits with a rate between 0% and 0.05% has been hovering at around two-thirds since 2017). The share of household deposits priced at negative rates is negligible for longer term deposits, while the corresponding share for overnight deposits has started increasing more recently, reaching 7% as at September 2020. Negative rates in this segment are observed only in some euro area countries (Germany, Italy, Cyprus, the Netherlands, Finland and Belgium). Corporate deposits are subject to negative rates in both the longer-term and the overnight segments, the latter being by far the most relevant category. Nonetheless, the shape of the cross-bank distribution of the rates applied to corporate deposits shows a progressive and visible compression of the mass at zero (see Chart B.3, upper panel).

A number of structural features of the economy may explain the relevance and persistence of the zero lower bound on deposit rates. As mentioned above, the leeway to charge negative rates is considerably smaller for deposits made by households. For corporate deposits, existing analyses illustrate that negative rates are more likely to be passed through by stronger banks.^[11] Moreover, banks charging negative rates on NFC overnight deposits tend to be those dealing with larger clients (see Chart B.3, lower panel). This is consistent with the hypothesis that the size of the deposit and the complexity of the available payment services largely determine the transaction costs that firms would face if they had to turn these deposits which are mostly used to manage their liquidity and payments into cash. Accordingly, banks operating with smaller clients or in countries dominated by smaller firms may have only limited headroom to overcome the zero lower bound on these deposits.

Looking ahead, banks in the euro area may find it increasingly difficult to continue charging negative rates on a significant share of their deposits. Market rates are expected to remain at historically low levels for a long time, largely due to developments in the structural factors underpinning the low-rate environment. Consequently, the sluggishness by which banks charge negative deposit rates more extensively will have a continuing impact on their margins and profitability. While euro area banks can mitigate the costs associated with the zero lower bound by relying more heavily on other sources of funding such as central banks or financial markets, this strategy may also be subject to constraints. Retail deposits, which represent the largest single item in banks’ funding structure (44% of total funding in July 2020, in line with the traditional role of maturity transformation), matter for the formation of not only net interest income but also net fee and commission income, as payments and other deposit-related services generate a large volume of fees.

4 Conclusion

The impact of the low real and nominal interest rate environment on euro area banks’ profitability prospects needs to be considered in the new economic context. Prior to the pandemic, there was already a debate as to whether the balance between supportive and dampening effects of low interest rates on euro area bank profitability was changing. The main supportive effects come from the positive impact of low interest rates on the economic outlook, decreasing loan losses due to improved borrower creditworthiness, and increasing intermediation volumes. The dampening effects studied in this special feature, reflect the negative impact of low rates on net interest margins. Expectations are now for historically low rates to remain for even longer, still driven largely by real interest rates.

The findings in this special feature suggest that the longer interest rates remain low, and in the absence of a rebound in inflation expectations, the more of a drag on euro area bank net interest margins they can become. This has relevance for the current context, where the extended persistence of the low interest rate environment comes on the back of a decade of low rates and has been accompanied by a large swathe of benchmark rates below zero. The findings of this analysis of euro area banks’ past performance suggest that these conditions are consistent with pressure on net interest margins and net interest incomes. This is especially likely if the pass-through of negative interest rates continues to remain sluggish. While low rates should help keep the cost of risk lower than otherwise, an increasing drag from squeezed margins is, other things being equal, a significant challenge to bank profitability.