Financial AI: Benefit or Danger? I don’t Know.
There's a debate ongoing in the UK at the moment around a cash-only tax-advantaged account, and if the benefit should be reduced from a yearly £20,000 deposit allowance to £4,000. This is with the aim of making people favor equity-based, tax-advantaged accounts to enhance returns. Very UK specific, but it got me thinking once again about the general idea of holding cash as a defensive asset in your portfolio for sequence of returns (SOR) risk when in retirement.
Truthfully, the maths was beyond me for a quick article, but I thought this was maybe something I could test with one of the shiny new LLMs that are popping up everywhere. I chose Google's Gemini, and after politely introducing myself, I posed a question:
"Can you quantify the difference on a standard 60:40 $1,000,000 portfolio of holding a five-year cash buffer during a three-year 20% market drawdown, and project out to two years after the recovery at average market returns?" Here's the LLM's condensed summary:
"For retirees with a $1,000,000 60:40 portfolio, a $200,000 (5-year) cash buffer significantly mitigates 'sequence of returns risk.' Our analysis shows that during a hypothetical 3-year, 20% market drawdown, the buffered portfolio avoids forced selling of depressed assets. After the drawdown and two subsequent years of average returns, the portfolio with the cash buffer would be worth $916,649. The unbuffered portfolio, forced to sell assets at a loss, would stand at $886,906. This $29,743 difference highlights the cash buffer's crucial role in preserving capital and enhancing long-term portfolio resilience, especially when regular withdrawals are necessary. It demonstrates how avoiding sales during downturns allows the invested portion to recover on a larger base, ensuring greater financial stability."
This seems a reasonable outcome to me and highlights a possible benefit of holding cash if you are of the opinion there's going to be a large prolonged drawdown. Then again I've no clue about the calculations the AI used to come to these conclusions.
But what has captured my imagination, and is, I think, something worthy of serious debate going forward as these AI systems develop in complexity in the coming years: Could this be the start of a democratization of financial advice for each individual, with the ability to perform very powerful financial simulations on portfolios that only a few years ago would have been nearly impossible? There are deep implications for this going forward.
I can think of a few areas of concern. When I was a young teenager, I loved programming but always had to be careful of the "garbage in, garbage out" mantra. This would definitely apply here. Other things that come to mind include fundamentally trusting the outputs and issues with privacy of the data used in the simulations, maybe even people over-relying on their AI models. But it offers intriguing possibilities for personal portfolio management in the coming decade and I think very new and unique dangers to navigate.
The simple fact that this morning I could, within minutes of watching a news article, come up with a powerful simulation using an AI is thought-provoking and, in some ways, an alarming demonstration of technological advancement. Let's hope we can successfully embrace its benefits.
Truthfully, the maths was beyond me for a quick article, but I thought this was maybe something I could test with one of the shiny new LLMs that are popping up everywhere. I chose Google's Gemini, and after politely introducing myself, I posed a question:
"Can you quantify the difference on a standard 60:40 $1,000,000 portfolio of holding a five-year cash buffer during a three-year 20% market drawdown, and project out to two years after the recovery at average market returns?" Here's the LLM's condensed summary:
"For retirees with a $1,000,000 60:40 portfolio, a $200,000 (5-year) cash buffer significantly mitigates 'sequence of returns risk.' Our analysis shows that during a hypothetical 3-year, 20% market drawdown, the buffered portfolio avoids forced selling of depressed assets. After the drawdown and two subsequent years of average returns, the portfolio with the cash buffer would be worth $916,649. The unbuffered portfolio, forced to sell assets at a loss, would stand at $886,906. This $29,743 difference highlights the cash buffer's crucial role in preserving capital and enhancing long-term portfolio resilience, especially when regular withdrawals are necessary. It demonstrates how avoiding sales during downturns allows the invested portion to recover on a larger base, ensuring greater financial stability."
This seems a reasonable outcome to me and highlights a possible benefit of holding cash if you are of the opinion there's going to be a large prolonged drawdown. Then again I've no clue about the calculations the AI used to come to these conclusions.
But what has captured my imagination, and is, I think, something worthy of serious debate going forward as these AI systems develop in complexity in the coming years: Could this be the start of a democratization of financial advice for each individual, with the ability to perform very powerful financial simulations on portfolios that only a few years ago would have been nearly impossible? There are deep implications for this going forward.
I can think of a few areas of concern. When I was a young teenager, I loved programming but always had to be careful of the "garbage in, garbage out" mantra. This would definitely apply here. Other things that come to mind include fundamentally trusting the outputs and issues with privacy of the data used in the simulations, maybe even people over-relying on their AI models. But it offers intriguing possibilities for personal portfolio management in the coming decade and I think very new and unique dangers to navigate.
The simple fact that this morning I could, within minutes of watching a news article, come up with a powerful simulation using an AI is thought-provoking and, in some ways, an alarming demonstration of technological advancement. Let's hope we can successfully embrace its benefits.
The post Financial AI: Benefit or Danger? I don’t Know. appeared first on HumbleDollar.
No comments have been added yet.
