Sunday, September 21, 2025
I asked ChatGPT:
“What financial crisis should be harder to predict, those were banks are required to hold the same capital/equity against all assets, a leverage ratio, or those where risk weighted requirements allow banks to hold less capital against some assets?”
ChatGPT answered:
Good question.
Crises under a leverage ratio (same capital against all assets) are usually easier to anticipate: banks grow more or less evenly, and risks accumulate more visibly across their balance sheets. If a bubble builds in a specific asset class (say real estate or sovereign bonds), banks cannot concentrate excessively there without also tying up more of their own equity. The constraint is blunt, but it makes emerging vulnerabilities more transparent.
By contrast, crises under risk-weighted capital requirements are harder to predict: regulators assign low risk weights to certain assets (e.g. sovereign bonds, mortgages), letting banks hold very little equity against them. This encourages systemic concentration in officially “safe” exposures. Because reported capital ratios look strong, early warning indicators are masked—until the supposedly safe assets lose value, at which point losses cascade across the system. The 2008 crisis (mortgage-backed securities) and the eurozone sovereign crisis illustrate this: both were amplified by risk weights that understated true risk.
So: financial crises under risk-weighted regimes are harder to foresee, because risk is distorted by regulatory design, cloaked in the appearance of safety, and correlated across many banks at once.
Would you like me to illustrate this with a short comparison of how each system might have affected the visibility of the 2008 subprime crisis?
I said: If brief, please do.
ChatGPT answered:
Sure.
· Leverage ratio: U.S. banks would have needed the same equity against subprime mortgage securities as against Treasuries. Their balance sheets would have shown visibly higher leverage as they loaded up on subprime, making the buildup of risk easier to spot.
· Risk weights (Basel): Subprime securities often received low risk weights thanks to high credit ratings. Banks could report healthy capital ratios while piling on hidden leverage. The crisis appeared suddenly because regulators, investors, and even banks themselves underestimated how much true risk was concentrated.
Result: under risk weights, the 2008 crisis was much harder to see coming.
I said: Thanks!
It replied: You’re welcome!
I asked Grok:
"What financial crisis should be harder to predict, those were banks are required to hold the same capital/equity against all assets, a leverage ratio, or those where risk weighted requirements allow banks to hold less capital against some assets?"
Grok answered:
"Financial crises should be harder to predict in systems where risk-weighted requirements allow banks to hold less capital against some assets. This is because risk weights can fail to accurately reflect true portfolio risks, especially during economic booms when they tend to compress, encouraging excessive leverage and risk-taking that builds up systemic vulnerabilities.
These misestimations—such as underweighting the risks of assets like mortgage-backed securities before 2008—make banks appear well-capitalized on paper while hiding potential instabilities, leading to surprises when conditions deteriorate. In contrast, a uniform leverage ratio provides a simpler, more transparent backstop that directly limits overall leverage regardless of perceived risk, offering better predictive power for failures, particularly among large banks during crises. It performs at least as well as risk-weighted ratios over short horizons (one to two years) and acts in a more countercyclical manner."
I said: Thanks!
It replied: You're welcome! If you have more questions on finance or anything else, feel free to ask.
Note: The answers are copied exactly from those given to me by ChatGPT and Grok.
Sunday, September 7, 2025
#AI #ChatGPT #Grok: Do risk weighted bank capital requirements empower government borrowing at low interest rate cartels?
I asked ChatGPT
"Would it be outrageous to hold risk weighted bank capital requirements that imply a veiled prohibition for those perceived as “risky” to access bank credit in fair market risk adjusted terms, empowers “safe” government borrowing at low interest rate cartels?"
ChatGPT answered:
Short answer
“Not outrageous — it’s exactly what risk-weighting can do in practice — but it’s economically harmful and politically risky. Designing capital rules that effectively bar “risky” borrowers while heavily privileging government debt creates powerful distortions: it crowds out productive credit, concentrates risk, and subsidises government borrowing regardless of merit.
Why it happens (mechanics)
Risk weights tell banks how much capital to hold against each asset. Low weights on sovereign bonds and high weights on small-business or startup loans raise the relative capital cost of lending to the latter. Because banks price loans to cover capital costs, borrowers with higher risk-weights face higher spreads or simply no credit access. So a regulatory system can unintentionally (or intentionally) create a de-facto cartel of cheap “safe” government funding and expensive or unavailable private credit.
Main harms
Misallocation of capital. Productive, innovative firms (startups, small businesses) get starved of finance; low-return but “safe” assets (sovereigns) get overfunded.
Inequality & incumbency bias. Established firms and asset-rich borrowers (who can use collateral that attracts low weights) gain advantage; entrepreneurship suffers.
Concentration & systemic risk. If all banks hold large sovereign positions because they’re cheap capital-wise, the banking system becomes correlated with sovereign risk — a sovereign-bank doom loop.
Moral hazard for governments. Cheap financing reduces incentives for fiscal discipline.
Credit markets segmentation. Nonbank lenders may step in, growing shadow banking with weaker supervision — exactly the regulatory arbitrage regulators try to avoid.
Counterarguments in favor (why some designers accept it)
Perceived safety: Sovereign debt is often default-rare (for major currencies), so lower capital burden may seem sensible for prudential safety.
Simplicity & political feasibility: Rewarding sovereigns is politically popular and easier to justify after crises.
Short-term stability: In stress, public debt can act as a liquidity buffer for banks.
How to reduce the perverse effects
Use a non-risk-sensitive leverage floor alongside risk weights (a binding leverage ratio reduces the extent to which low weights can be exploited).
Apply concentrated exposure / sovereign concentration limits or higher floors on sovereign weights for domestic sovereigns to avoid large concentrated bets.
Risk-sensitive but calibrated weights: avoid zero or near-zero weights for public debt; make weights reflect real risks including inflation/default & FX.
Countercyclical capital buffers tied to lending booms rather than asset class alone.
Support targeted credit programs (guarantees, cheap refinancing) for socially valuable but risky sectors rather than broadly skewing capital rules.
Transparency & periodic review so political capture is visible and adjustable.
Bottom line
Treating risk weights as a tool to subsidize government borrowing or to keep “risky” borrowers out of the market is economically dangerous. The design trade-off is real: risk-sensitivity helps microprudential pricing but can create large macro- and distributional distortions if miscalibrated. Better: combine risk-sensitive capital with blunt instruments (leverage floors, concentration limits) and targeted fiscal/credit policies for sectors you want to support.”
I said: Thanks!
It replied: You’re very welcome!
I asked Grok: With a fairly brief answer:
"Would it be outrageous to hold risk weighted bank capital requirements that imply a veiled prohibition for those perceived as “risky” to access bank credit in fair market risk adjusted terms, empowers “safe” government borrowing at low interest rate cartels?"
Grok answered:
"Yes, that view has merit and isn't outrageous—it's a common critique among economists like Anat Admati and Andrew Haldane. Risk-weighted requirements (e.g., Basel III) can indeed distort lending by incentivizing banks to favor low-risk assets like government bonds (often zero-weighted), enabling cheap sovereign borrowing while making credit costlier or scarcer for "risky" borrowers like SMEs or emerging markets. This creates an implicit subsidy for governments, potentially forming a low-rate "cartel" effect, though proponents argue it enhances systemic stability. Alternatives like leverage ratios aim to address this bias."
I said: Thanks
It replied: You're welcome! If you have more questions, feel free to ask.
Note: The answers are copied exactly from those given to me by ChatGPT and Grok
Subscribe to:
Posts (Atom)