top of page
Writer's pictureWilliam Webster

Guesswork

  • The Bank of England commissioned Dr. Bernanke's report, "Forecasting for Monetary Policy Making and Communication at the Bank of England: A Review."

  • We use AI to get a summary, try it for yourself and do a Q&A;

  • Banks and Building Societies can use this as a catalyst to enhance their own forecasting, particularly for managing interest rate risk;

  • AI can provide hypothetical advice on balance sheet management, such as using forward rates, and stress-testing unhedged positions; I ask Claude to write like Ben Bernanke - a novel way of using AI to think like an expert;

  • AI in this persona can facilitate valuable discussions on an institution's readiness for rate shocks by generating extreme tail risk scenarios and their potential impact on interest rates;

  • Through dialogue, AI is changing what we do and it’s a lot more interesting to work like this.

 

As I'm sure you are aware, the Bank of England has been concerned about its ability to model the future. Whilst I'm of the school that much modelling is guesswork and that forward rates are the wisdom of crowds, many financial institutions prefer to put their interpretation on what may or may not happen.

 

In this article, AI provides a very brief summary of Dr. Bernanke's report, "Forecasting for Monetary Policy Making and Communication at the Bank of England: A Review." For an in-depth read, you need the PDF from the Bank of England website, and if you are feeling experimental, upload it to a large language model and engage in a Q&A session.


As I write this, it reminds me that the world has changed. Before AI, lengthy documents had to be read to get insight. Now, there are faster and arguably better alternatives using AI, and long documents can be repurposed for the reader.


But that’s not all; it's far easier to take some of the suggestions contained in the report and then apply them to your own business. All you have to do is prompt AI, and this is much more engaging than having to do all the work yourself; in fact, working with AI is like having a conversation, and for many people, that can be fun. Let's have a look at what GenAI makes of Dr. Bernanke's report. I asked ClaudeOpus for a summary:


"The key points of the report "Forecasting for Monetary Policy Making and Communication at the Bank of England: A Review" by Dr. Ben Bernanke are:

 

  1. The report reviews economic forecasting at the Bank of England, focusing on how forecasting can better support policymaking and communication during times of high uncertainty.

  2. The report makes recommendations to: Improve and maintain the Bank's forecasting infrastructure, including data management, software, and economic models. Support effective policymaking by equipping the MPC and staff to learn from past forecast errors, identify risks, and deal with uncertainty. Help the MPC better communicate its economic outlook, risks, and the basis for policy choices.

  3. Serious problems were found with the Bank's outdated forecasting infrastructure, which limits analysis. Upgrading data management is underway, but economic models also need maintenance and updating.

  4. The forecast process should highlight significant errors and evaluate models, judgements, and assumptions. Alternative scenarios should compare policy choices and assess risks.

  5. The central forecast is emphasized in the Bank's communications, but has drawbacks. Publishing selected alternative scenarios would improve communication of the outlook, risks, and policy rationale.

  6. Despite deficiencies, the Bank's overall forecasting accuracy in recent tumultuous years was comparable to peer central banks and external forecasters. But the experience provides motivation to review forecasting processes.

In summary, the report recommends infrastructure upgrades, expanded use of alternative scenarios in policymaking and communication, and reconsidering the emphasis on the central forecast to strengthen the Bank's economic analysis and transparency".

 

Using the Review as a Catalyst


If the Bank of England has felt it worthwhile to overhaul this area of their work, I wonder whether some of the insights from the review can be used by banks and building societies to enhance their own forecasting models in times of uncertainty. I put this to Claude, and the response is:

 

"The bank may want to consider conducting a comprehensive assessment of its current forecasting infrastructure. This could involve identifying potential areas for enhancement and investment related to data management, software tools, and economic models.

 

Another idea is to develop a structured approach for periodically evaluating the bank's forecast performance, underlying models, key judgements, and assumptions. Insights gleaned from this review process could then be incorporated into future decision-making.

 

To better assess risks and inform strategic choices, the bank might explore integrating alternative scenarios into its forecasting and planning processes. This can provide a more robust view of potential economic outcomes.

 

The bank may also want to look at ways to enhance its stakeholder communications. Offering a clearer and more detailed perspective on the economic outlook, risks, and rationale behind decisions can foster greater understanding and engagement.

 

Finally, the bank could benefit from keeping abreast of evolving best practices in the forecasting field. Maintaining an active dialogue with industry peers to exchange ideas and experiences may also yield valuable insights for the bank to consider".


Balance Sheet Positioning

 

I want to explore a specific area - positioning the balance sheet for interest rate risk. This is often done by examining forward rates and then overlaying management judgement, which is used in the hedging strategy. Simply put, the balance sheet is managed based on the judgement of future rates and within the risk tolerances considered acceptable. It sounds like science, but it is far from it.

 

Wouldn’t it be interesting to get Dr. Bernanke’s view on this?


One of the things I've learned when using GenAI is that you can prompt it to adopt a persona; just ask it to imagine it's Warren Buffett, Jim Slater, or someone else, and it will. It's as if the essence of the individual and their thinking is concentrated in the name. I suspect this is due to the way GenAI has been trained, and the name acts as a sort of magnet for a particular line of thinking, which is then used in its output.


Let's now ask Claude to assume the persona of Ben Bernanke and give us some advice on managing the balance sheet; here is part of the result:

 

 "Adopting forward rates as the base model and then stress-testing unhedged positions for tail events is indeed a prudent approach to managing your bank's interest rate risk within your risk appetite. Let me elaborate on this:

 

  1. Adopt forward rates as the base model:

  • Use market-implied forward rates as the foundation for your interest rate modeling and forecasting.

  • Regularly update your forward rate curves to reflect the most current market expectations.

  • Incorporate forward rates into your hedging strategies and mortgage pricing decisions.


Rationale: Forward rates provide an objective, market-based view of future interest rate expectations. By aligning your base model with market consensus, you can make more informed decisions and reduce the potential impact of individual biases.


2. Explore tail events on unhedged positions:

  • Identify and quantify your bank's unhedged interest rate exposures, particularly in your mortgage portfolio.

  • Conduct stress tests and scenario analyses to assess the potential impact of extreme interest rate movements on these unhedged positions.

  • Evaluate the resulting downside risks and determine if they fall within your bank's risk appetite.

Rationale: While hedging can mitigate interest rate risk, it's crucial to understand the potential consequences of tail events on any remaining unhedged exposures. By stress-testing these positions, you can gauge the potential downside risk and make informed decisions about whether to accept, mitigate, or transfer that risk.


3. Ensure clear understanding and alignment with risk appetite:

  • Clearly define and communicate your bank's risk appetite, particularly with regard to interest rate risk.

  • Regularly assess whether your interest rate risk exposure, as determined by your stress tests and scenario analyses, aligns with your stated risk appetite.

  • Make adjustments to your hedging strategies, product mix, or pricing as necessary to maintain alignment with your risk appetite.

Rationale: A clear understanding of your bank's risk appetite is essential for effective risk management. By consistently ensuring that your interest rate risk exposure remains within your defined risk appetite, you can protect your bank's financial stability and make more informed strategic decisions.


By adopting forward rates as your base model, exploring tail events on unhedged positions, and ensuring clear alignment with your risk appetite, you can create a robust framework for managing interest rate risk within your bank's constraints. This approach will help you make better-informed decisions, protect against downside risks, and allocate your limited resources effectively".


The tail risk problem is very relevant; after all, it is the tail risk that will potentially get us into trouble, and this is something we need to know about. One way we can explore this is by building scenarios.


Again, I ask the Bernanke Claude persona for guidance; here is part of the response:

 

"To help you better understand and prepare for tail risks, I've designed three extreme events that could lead to significant movements in interest rates. For each event, I'll provide a brief description and an estimate of where the Bank of England's Bank Rate might stand in the aftermath, given its current level of 5.25%.


  1. Severe Global Economic Recession: Description: A severe and prolonged global economic downturn, triggered by a combination of factors such as a major financial crisis, geopolitical tensions, and a collapse in consumer and business confidence. The recession leads to a sharp contraction in global trade, rising unemployment, and deflationary pressures. Estimated Bank Rate: In this scenario, the Bank of England would likely cut the Bank Rate aggressively to stimulate the economy and combat deflationary risks. The Bank Rate could potentially fall to 0.5% or even lower, depending on the severity and duration of the recession.

  2. Unexpectedly High and Persistent Inflation: Description: A scenario in which inflation surges well above the Bank of England's 2% target and remains persistently high due to a combination of factors such as supply chain disruptions, energy price shocks, and a significant expansion in fiscal spending. The high inflation expectations become entrenched, leading to a wage-price spiral. Estimated Bank Rate: To combat the inflationary pressures, the Bank of England would likely raise the Bank Rate significantly. In this scenario, the Bank Rate could potentially rise to 8% or higher, depending on the level of inflation and the effectiveness of monetary policy in anchoring inflation expectations.

  3. Major Geopolitical Conflict: Description: A significant escalation in geopolitical tensions, leading to a large-scale military conflict involving major global powers. The conflict disrupts global trade, energy supplies, and financial markets, causing a surge in risk aversion and a flight to safe-haven assets. Estimated Bank Rate: The impact on the Bank Rate would depend on the balance of recessionary and inflationary pressures resulting from the conflict. If the conflict primarily leads to a global economic downturn and financial market stress, the Bank of England might cut the Bank Rate to support the economy, potentially to 2% or lower. However, if the conflict also results in supply-side disruptions and inflationary pressures, the Bank Rate might remain unchanged or even increase moderately to balance growth and inflation risks".

 

These events are based on opinion rather than fact, and indeed, that's what stress testing is about; it's not a science, nor is it an art—it's a mixture of both. For any institution interested in examining its tail exposures, using GenAI in this way to explain some of the nuances that could unfold is a starting point for a valuable discussion about how rates and liquidity could move and whether the institution is capable of handling such disruption in a short period. It would be very easy to continue our discussion with GenAI and build on what we have so far.


Not so long ago, if we had the time, we would have read Dr. Bernanke’s report and left it at that. Now, you can get the key information and drill down as you like. AI simply acts as your research assistant. But that’s just a start.


You can now consider using the report as a catalyst for change in your business. AI can make suggestions that you can follow up on. You can also marshal the wisdom of the persona to improve the way you work. From my experience, this can be very powerful. It captures the essence of the expert and gives us insights we would never have been able to obtain otherwise. Why not try it out?


We live in interesting times. If you've enjoyed reading this and find it helpful, I'll be pleased to hear from you.

 

6 views

Recent Posts

See All
bottom of page