Trying out AI - Rebalancing my Investments

I keep looking for ways to leverage AI both at work and in my personal life. Recently, I asked for help rebalancing my portfolio. The following is a series of prompts that I used to get there.

The first step was to document my holdings. I have accounts across several management companies and about 100 different assets. I tried to export them from each company, but none had an export feature. This is where I started using ChatGPT to parse my statements and export them as a table. 

Using the attached investment account statement, extract the current holdings from the document and give them back to me as a CSV file.

I worked with ChatGPT to correct this, as it would only read a page of the data. We went back and forth several times before I got the results I needed, including looking up the expense ratio for every mutual fund and EFT. Next, I described how I wanted my portfolio to be rebalanced.

   

Balance my portfolio rooted in Nobel Prize-winning economic theories would emphasize diversification, broad market exposure, and risk management. Allocating across asset classes using the following: Portfolio Allocation Equities (60%-70%) Domestic Equity (35%-40%): Broad exposure to U.S. stocks via total market or S&P 500 index funds. Include a small-cap tilt (e.g., small-cap value funds) to capture the small-cap premium identified by Fama and French. International Equity (20%-25%): Diversify across developed markets and emerging markets. Consider including small-cap international funds to enhance diversification and returns. Value Tilt (10%-15%): Increase allocation to funds focusing on value stocks (high book-to-market ratios) to capture the value premium Fixed Income (30%-40%) Domestic Bonds (20%-25%): Investment-grade government and corporate bonds for stability. A portion in inflation-protected securities (e.g., TIPS) to guard against inflation risks. International Bonds (10%-15%): Include exposure to developed market and emerging market bonds to diversify currency and interest rate risks. Alternative Assets (Optional: 5%-10%) Real estate investment trusts (REITs) for exposure to real estate. Commodities or other diversifying assets if aligned with the investor’s goals. Cash and Cash Equivalents (5%-10%) For liquidity and short-term needs, including high-yield savings, money market funds, or short-duration Treasury bonds. Design Principles Market Efficiency: Avoid active stock picking or market timing, as the Efficient Market Hypothesis suggests these strategies rarely outperform Diversification: Use a fund-of-funds approach to spread investments across many asset classes, sectors, and geographic regions, reducing unsystematic risk. Small-Cap and Value Tilt: Emphasize small-cap and value stocks to capitalize on their historical outperformance as identified in the Fama-French Three-Factor Model. Risk Management: Use a mix of equity and fixed-income securities to align with the investor’s risk tolerance and investment horizon, reflecting principles of Modern Portfolio Theory. Low Costs: Prefer passive index funds or ETFs to minimize expenses and maximize net returns. The attached file lists my holdings across accounts, with the last column being the account name those holdings are in. Balance all my holdings listing unique transactions. Below is a table with a list of my holdings across accounts. The first row is the column names. The last column being the account name those holdings are in.

It took a bit of coaxing to get a final portfolio. First, I have my holdings across five separate accounts, and getting ChatGPT to balance across accounts took a bit prompting. Some accounts had cash that would not get invested, so I had to remind it that the goal was to have between 5-10%. Another prompt resulted in more mutual funds with high cost ratios, which I wanted to minimize. So I added a prompt specifying that any mutual fund or ETF should have a cost ratio of .05%.

Once I had a portfolio rebalancing working the way I wanted, I asked for a list of transactions needed to achive that portfolio. This resulted in some wierd side effects where there were too many trades resulting in lots of transaction fees, so I added an instruction to minimize the number of trades. If I already owned Apple in one account, don't sell it if also going to buy it in another account.

I ended up with a list of trades to perform across each account. I don't know about you, but I have taken notice of that warning at the bottom of the screen recommending that any output should be double checked. So that set of prompts began.

I asked for the detailsof why each security was chosen, what rule(s) / criteria were used and what the amount specific was chosen. The output was very informative and is what I used to check the BUY transactions specified. I didn't find anything wrong. I further probed by asking which other securities were considered for each buy and why the one recommened was selected over the others. The following is one of the securities from that details.

Fund Selected: Fidelity Total Market Index Fund (FSKAX) • Expense Ratio: 0.015% Selection Logic: • Broad Market Exposure: FSKAX tracks the Dow Jones U.S. Total Stock Market Index, providing comprehensive exposure to the entire U.S. equity market, including large-cap, mid-cap, and small-cap stocks. • Low Expense Ratio: At 0.015%, it is one of the lowest-cost options available, aligning with your preference for minimizing expenses. • Fund Size and Liquidity: With significant AUM, it offers high liquidity and stability. • Alignment with Strategy: Provides a foundation for the Domestic Equity portion of your portfolio, supporting diversification and market efficiency principles. Other Assets Considered: • Vanguard Total Stock Market Index Fund (VTSAX): Expense Ratio of 0.04%. Not selected due to a higher expense ratio compared to FSKAX. • Schwab Total Stock Market Index Fund (SWTSX): Expense Ratio of 0.03%. FSKAX was preferred due to the existing relationship with Fidelity and slightly lower expense ratio.

I found this all very helpful and it helped me to trust (or not) the trades recommended. 

What have I done with all this information? Nothing, yet. It's not clear to me if this was anything more than an intellectual excersize. It was very cool and I learned a couple of things - patience being a big one. It took me four days to complete all of this.