Category: Financial Stability

Demographics, deposits and data: using machine learning to segment UK mortgages

Joe Grimshaw

Who are the UK’s mortgage borrowers, and how do their characteristics differ? Despite extensive literature on mortgage profiles, loan-level segmentation remains limited, existing work relies on aggregates or predefined categories. I address this gap by applying unsupervised machine learning to 20 years of data, allowing the model determine segments without prior assumptions. Three clusters emerge: one with low leverage, and two with high leverage but notably different income profiles. Lending composition has shifted gradually. High leverage, high-income borrowers now account for a larger market share, and first-time buyers increasingly fall into more leveraged segments. Machine learning is crucial for financial stability, revealing concentrations of characteristics, and trends, that aggregates and simple splits cannot, offering richer and earlier indications of potential vulnerabilities.

Continue reading “Demographics, deposits and data: using machine learning to segment UK mortgages” →

Credit constraints and housing market access

Belinda Tracey and Neeltje van Horen

The Help-to-Buy (HTB) programme introduced in 2013 reopened the 95% loan to value (LTV) segment of the UK mortgage market, thereby reducing the minimum deposit requirement for many first-time buyers (FTBs) from 10% to 5% (Chart 1). That policy change offers a useful natural experiment to study how deposit constraints shape access to homeownership. We previously demonstrated that this easing of deposit constraints generated a clear increase in local spending. In a recent paper, we show that lowering this constraint increases FTB home purchases, particularly among households without access to external financial support for their deposit.

Continue reading “Credit constraints and housing market access” →

Explainability in machine learning: do popular methods deliver on their promises?

Ivona Cickovic and Andrea Serafino

Machine learning models are increasingly used in organisational decision-making, yet their inner workings often remain opaque. When these systems influence real world outcomes, knowing what they predict is not enough – we also need to understand why. Explainability methods aim to illuminate this ‘black box,’ and feature attribution tools that link predictions to individual inputs are especially popular. They feel intuitive but rely on strict data assumptions that rarely hold, making their outputs unreliable. The 2019 Apple Card case illustrates why this matters: despite gender not being an explicit input, women appeared to receive lower credit limits than men with similar profiles – an outcome attribution methods struggle to explain. This post examines a key assumption underpinning these tools and how it distorts explanations.

Continue reading “Explainability in machine learning: do popular methods deliver on their promises?” →

Opening the floodgates? Modelling spillovers from flood insurance protection gaps to UK mortgages

Will Banks and Kemal Erçevik

When extreme weather hits, households typically turn to insurers to cushion the financial blow. But rising temperatures and greater exposure in high-risk areas could test the insurance sector’s capacity to absorb such losses. As the Financial Policy Committee has highlighted, climate change could create insurance protection gaps, leaving households vulnerable and shifting risks across the financial system. We have built a model to estimate potential protection gaps, finding that – under conservative assumptions – the share of UK mortgagors uninsured could increase from 5% today to around 7%–10% in 2050, or up to 16% following a severe flood event. While this would have substantial welfare implications, our model suggests the aggregate impact on lenders would be small compared to previous financial crises.

Continue reading “Opening the floodgates? Modelling spillovers from flood insurance protection gaps to UK mortgages” →

Bond financing conditions and economic activity in the UK: aggregate and firm-level evidence

Eduardo Maqui, Nicholas Vause and Márcia Silva-Pereira

In recent decades, the corporate bond market has grown from a relatively niche source of finance for UK corporations to a central pillar alongside bank loans. This transition raises an important question: as with bank credit conditions, have supply conditions in the corporate bond market come to significantly affect UK economic activity? Our recent research suggests the answer is a resounding yes. We show that a measure of corporate bond financing conditions − the Excess Bond Premium (EBP) − not only anticipates macroeconomic outturns in the UK, but also influences investment by UK firms, especially those that are highly leveraged and more reliant on bond finance.

Continue reading “Bond financing conditions and economic activity in the UK: aggregate and firm-level evidence” →

Monetary policy, state-dependent bank capital requirements and the role of non-bank financial intermediaries

Manuel Gloria and Chiara Punzo

The expansion of non-bank financial institutions (NBFIs) is transforming the financial landscape and introducing fresh challenges for financial stability and oversight at the same time as creating opportunities. Using a dynamic stochastic general equilibrium (DSGE) model, we find that while NBFIs may enhance long-term welfare for households and entrepreneurs in normal conditions, their greater role also heightens vulnerabilities to severe shocks in the financial system. Greater NBFI activity boosts competition in the financial sector, leading to more efficient resource allocation. A working paper detailing these results was recently published.

Continue reading “Monetary policy, state-dependent bank capital requirements and the role of non-bank financial intermediaries” →

Measuring banking resilience to adverse outcomes

Giovanni Covi and Tihana Škrinjarić

The ability of the banking system to absorb shocks and continue providing vital financial services is important because it underpins the smooth functioning of the broader economy. We propose a methodology that serves as a valuable tool for monitoring banking system stability. It quantifies the resilience of the banking system given the prevailing macrofinancial risk environment. The main measure we derive is the probability that one or more banks will fail to meet regulatory capital or liquidity requirements within a given horizon.

Continue reading “Measuring banking resilience to adverse outcomes” →

The Bank Underground Christmas Quiz 2025

Image of the Bank of England during Winter with partial snowfall.

Bank Underground is about to take a break for the festive season. In keeping with tradition, we are pleased to present the annual Bank Underground Christmas Quiz! This year, it’s been prepared with the kind assistance of the Bank of England’s Archive team. We hope you enjoy testing your knowledge of the Bank’s history, especially how it has marked Christmas in years past. We wish our readers a very happy festive season!

Continue reading “The Bank Underground Christmas Quiz 2025” →

Who owns the buildings where Britain shops, works – and stores its data?

Katherine Blood

We have developed a new measure tracking UK commercial real estate (CRE) ownership at property level, mapping the latest investor landscape at end-2025 Q3 and its shift since the pandemic. Our estimates show a diversified, international base: overseas investors hold around one third of UK CRE, while private equity funds own 8% after post-pandemic growth. Investor-owned CRE has tilted towards warehouses, logistics, rental housing and properties serving innovation-led sectors – like data centres and life-sciences. Why does this matter? CRE ownership shapes how shocks play out – affecting refinancing waves, upgrade costs and valuation swings. History shows the sector has seen boom-bust cycles before and contributed to financial stability challenges in the UK and abroad.

Continue reading “Who owns the buildings where Britain shops, works – and stores its data?” →