I warned many about the coming crisis, long before it happened, on many occasions and in many places, even at the World Bank. The regulators did not want to listen and that´s ok, it usually happens, but what's not ok, is that they still do not seem to want to hear it. “We can easily forgive a child who is afraid of the dark; the real tragedy of life is when men are afraid of the light.” (Plato: 427 BC – 347 BC)
"If the risks for banking systems are much conditioned to how credit risks are perceived, would it not be useful to base the risk weighted bank capital requirements on the conditional probabilities?"
ChatGPT answered:
"Yes, incorporating conditional probabilities into risk-weighted bank capital requirements could provide a more accurate and nuanced assessment of credit risks. By considering conditional probabilities, the regulatory framework could account for the specific characteristics and circumstances that affect the likelihood of default or other credit events.
Conditional probabilities take into account the probability of an event occurring given that another event has already happened. In the context of credit risk, this means considering the probability of default or credit deterioration given specific credit rating categories or other relevant factors.
By utilizing conditional probabilities, regulators could tailor risk weights more precisely to reflect the true credit risk associated with different assets. This approach could help mitigate the potential for misalignment between risk weights and actual risk, which is important for maintaining the stability and soundness of the banking system.
It's worth noting that while incorporating conditional probabilities could enhance the accuracy of risk assessment, it may also increase complexity and require a more robust data infrastructure to gather and analyze the necessary information. Additionally, the challenge lies in establishing a reliable and consistent framework for determining conditional probabilities across various credit risk scenarios.
Regulatory frameworks like Basel III have introduced more sophisticated approaches, such as stress testing and the use of internal models, to better capture credit risk. While these frameworks may not explicitly employ Bayesian methods, they aim to improve the risk sensitivity of capital requirements and align them more closely with the underlying credit risks faced by banks.
In summary, incorporating conditional probabilities into risk-weighted bank capital requirements could be beneficial for a more precise assessment of credit risks, but it would require careful consideration of data, modeling techniques, and the overall complexity involved."
“Of course, AI can be helpful. Imagine if many decades ago it would have been able to recommend to the Basel Committee that when decreeing their risk weighted bank capital requirements, they should not ignore the Bayesian conditional probabilities.”
Grok commented:
"You’re spot-on that AI could have been a game-changer for the Basel Committee decades ago, particularly by highlighting the importance of Bayesian conditional probabilities.
Basel’s risk-weighted capital requirements (RWAs) rely on static risk weights (e.g., 0% for sovereigns, 100% for corporates), which ignore how risks interact dynamically. Bayesian methods, which update probabilities based on new evidence, could have exposed flaws in assuming assets like AAA-rated mortgage-backed securities (MBS) were inherently "safe." For instance:
Conditional Risks:A Bayesian approach might have flagged that the "safety" of AAA-rated MBS depended on housing prices not collapsing—a condition that wasn’t guaranteed. In 2007, few models accounted for correlated defaults across mortgage pools, a blind spot AI could have illuminated.
Dynamic Updating:AI trained on historical data could have warned that low default rates on mortgages pre-2008 were skewed by a credit boom, not structural safety, adjusting risk estimates as conditions changed.
A 2019 study in Journal of Financial Stability noted that machine learning models, incorporating Bayesian techniques, outperformed traditional risk models in predicting systemic banking crises by capturing non-linear dependencies.
Had the Basel Committee used such tools in the 1980s or 1990s, they might have designed more robust rules, avoiding the overconfidence in “safe” assets that you’ve critiqued. AI could still play this role today—advising regulators to stress-test assumptions and prioritize dynamic risk signals over rigid categories. But, as you imply, it’s a tool, not a replacement for human judgment or market mechanisms."
Note: The answers are copied exactly from those given to me by ChatGPT and Grok
The less the perceived risk of default is, and the higher the leverage allowed, the greater the systemic risk.
My huge problem!
Q. "If Kurowski is right, why are his arguments so ignored? A. If I had argued that the regulators were 5 to 10 degrees wrong, I would be recognized, but since I am arguing they are 150 to 180 degrees wrong, I must be ignored.
The deafening noise of the Agendas
The fundamental reasons why it is so hard to advance the otherwise so easy explainable truth of this financial crisis, is because of the deafening noise of the Agendas…
On one side, we have the "progressives" who want to put all the blame on capitalistic banksters, and, on the other, the "conservatives" who want to blame the socialistic government sponsored enterprises GSEs of Fanny Mae and Freddy Mac.
For any of both sides accepting the fact that it was mostly a regulatory failure of monstrous proportions would seemingly be a highly inconvenient truth that would not help them to advance their respective agendas.
What is more dangerous in a systemic way, that which is perceived as risky or that which is perceived as not risky? Right!
How can the Basel Committee be so dumb?
Systemic risks is about something that can become as big so as to threaten the system… and our bank regulators in the Basel Committee are incapable or unwilling to understand that what has the largest possibilities of growing as big so as to threaten the system is what is perceived as having little or no risk, not what is perceived as risky… which makes their first and really only pillar of their regulations, that of capital requirements of banks that are lower when perceived risks are lower… so utterly dumb!
We must stop our gullible and naive financial regulators from believing in never-risk-land.
The stuff that bonuses are made of
Whenever a credit rating corresponds exactly to real underlying risk neither borrower nor lender loses but the intermediary cannot make profits… it is only when the credit ratings are too high or too low that those margins that can generate that profitable stuff that bonuses are paid for exist.
What were they thinking?
The default of a debtor is about the most common, natural and even benign risk in capitalism, so it is so hard to really get a grip on what was going around in the minds of the regulators when they decided to construe capital requirements for banks based exclusively on discriminating against that risk as it was perceived by some credit rating agencies.
Day by the day it is becoming more relevant... scary!
http://theaaa-bomb.blogspot.com
This I published in November 1999... Read it!
The possible Big Bang that scares me the most is the one that could happen the day those genius bank regulators in Basel, playing Gods, manage to introduce a systemic error in the financial system, which will cause the collapse of the OWB (the only bank in the world) or of the last financial dinosaur that survives at that moment.
Currently market forces favors the larger the entity is, be it banks, law firms, auditing firms, brokers, etc. Perhaps one of the things that the authorities could do, in order to diversify risks, is to create a tax on size.”
This I wrote, October 2004, as an Executive Director of the World Bank
We believe that much of the world’s financial markets are currently being dangerously overstretched through an exaggerated reliance on intrinsically weak financial models that are based on very short series of statistical evidence and very doubtful volatility assumptions.
Regulatory hubris
In a world with so many different risks, some naïve gullible and outright stupid regulators thought everything would be fine and dandy if they just had some few credit rating agencies determine default risks and then gave the banks great incentives, by means of different capital requirements, to follow those credit risk opinions.
On bs.
When experts bs..t the world that’s bad news, but when experts allowed themselves to be bs..ted by bs..ing experts that’s is when the world goes really bad.
This crisis resulted directly from the Potemkin credit ratings the market produced to satisfy the demand for AAAs created by the regulators.
Lower the capital requirements for banks on:
the loans to those who had nothing to do with creating the current AAA crisis, like small businesses and entrepreneurs but are anyhow the ones which most suffer the current scarcity of bank capital
My most current proposal on the regulatory reform for banks
They were supposed to teach the world prudent risk-taking and instead they taught it imprudent risk-aversion.
The deal!
This was the deal! If you convinced risky and broke Joe to take a $300.000 mortgage at 11 percent for 30 years and then, with more than a little help from the credit rating agencies, you could convince risk-adverse Fred that this mortgage, repackaged in a securitized version, and rated AAA, was so safe that a six percent return was quite adequate, then you could sell Fred the mortgage for $510.000. This would allow you and your partners in the set-up, to pocket a tidy profit of $210.000
Calling it quits?
A world that taxes risk-taking and subsidizes risk adverseness is a world that seems to want to lie down and die
Let´s neutralize the wimps!
If we are to keep on using Basel methodology for establishing the minimum capital requirements for banks, beside better risk weights, we must demand it also uses “societal purpose” weights.
What other word could describe a bank regulatory system designed exclusively to avoid bank crisis as if that is the only purpose of banking. You might just as well order the kids to stay in bed all life so as to diminish the risk of them tripping.
The minimum capital requirements of Basel that are based on default risks as measured by the credit rating agency amount to a dangerous tax on the risk, the oxygen of development.
Blindly focusing on default and leaving out any consideration that a credit with a low default risk but for a totally useless or perhaps even an environmentally dangerous purpose is much more risky for the society than a credit with a higher default risk destined to trying to help create decent jobs or diminish an environmental threat, is just silly.
But do I have to be disrespectful and call them silly? Well, individually perhaps they are not, but, as a group, bank regulators are so full of hot air that someone has to help them to puncture their cocoon balloon and let them out.
Breathe!
I’m going to third-pillar what?
By now the desperate bank regulators are throwing at us the third pillar of their Basel regulations which implies the need that we ourselves privately monitor our banks. Great, in my country, a couple of decades ago, I did just that and had a fairly good grip on whom of my banker neighbors were good bankers and whom to look out for.
But sincerely what am I supposed to do know when about 50 per cent of the retail deposits in my country are in hand of international banks (Spain) and that might be losing their shirt making investments in subprime mortgages in California?
Tragedy!
It is very sad when a developed nation decides making risk-adverseness the primary goal of their banking system and places itself voluntarily on the way down but it is a real tragedy when developing countries copycats it and fall into the trap of calling it quits.
Development rating agencies?
A bank should be more than a mattress!
When considering the role of the commercial banks should not the developing countries use development rating agencies instead of credit rating agencies?
Clearly more important than defending what we have is defending what we want to have.
What do we want from our banks?
Over the last two decades we have seen hundreds if not thousands of research papers, seminars, workshops conferences analyzing how to exorcize the risks out of banking; and if in that sense the bank regulation coming out from Basel was doing its job; and centred around words like soundness, stability, solvency, safeness and other synonyms. Not one of them discussed how the commercial banks were performing their other two traditional functions, namely to help to generate that economic growth that leads to the creation of decent jobs and the distribution of the financial resources into the hands of those capable of doing the most with it.
At this moment when we are suddenly faced with the possibilities that all the bank regulator’s risk adverseness might anyhow have come to naught, before digging deeper in the hole where we find ourselves fighting the risks, is it not time to take a step back and discuss again what it is we really want our commercial banks to do for us? I mean, if it is only to act as a safe mattress for our retail deposits then it would seem that could be taken cared of by authorizing them only to lend to the lender of last resort; but which of course would leave us with what to do about the growth and the distribution of opportunities.
We are suffering from more and more answers than questions begging for them, and so I work on the latter.
Read it all in my one and only book!"Voice and Noise"
Pssst... so few have read this book so it is slowly turning into a collector item (I do not say a "cult"... yet) and so you might benefit from getting your very own copy now.
Posts
