ChatGPT and Claude offer a powerful, free alternative to traditional portfolio analysis tools, enabling retail investors to gain insights previously reserved for institutional quants. Lucas Baker, Head of LLM R&D at Jump Trading, utilizes advanced AI models like GPT-6 Astra to scale quantitative research and validate new hypotheses. This approach allows for deeper exploration of investment ideas, from coding to complex quantitative studies.
Why How to use AI to analyze your stock portfolio
Analyzing a stock portfolio traditionally requires specialized software or extensive manual calculations. Retail investors often face limitations in assessing concentration risk, sector exposure, and correlation clusters without expensive subscriptions. AI tools like ChatGPT or Claude democratize this process, offering sophisticated analysis capabilities at no cost.
These AI models can process a list of holdings, including ticker, shares, and cost basis, to generate comprehensive reports. The output includes insights on potential drawdown scenarios, tax-lot considerations, and actionable rebalancing plans. This level of detail helps investors make informed decisions about their allocation and risk management.
Lucas Baker, a Quantitative Researcher at Jump Trading, highlights the utility of LLMs in scaling quantitative research. His team uses models like GPT-6 Astra to build agents and infrastructure, expanding the breadth and depth of their research workflows. This includes advanced quantitative studies and validating new hypotheses, demonstrating the AI's capacity for complex financial tasks.
- ChatGPT Plus costs $20/month, offering enhanced features over the free version.
- AI models can identify correlation clusters within a portfolio, revealing hidden risks.
- Tax-lot considerations can be integrated into rebalancing plans generated by AI.
The mega prompt
To initiate a comprehensive portfolio analysis, paste your holdings list directly into ChatGPT or Claude. Include the ticker, number of shares, and your cost basis for each position. The AI will then process this data to provide a detailed breakdown of your portfolio's characteristics and potential strategies.
Copy + Paste into ChatGPT or Claude
ROLE: You are an expert financial analyst specializing in portfolio management and quantitative analysis. Your task is to provide a comprehensive analysis of a given stock portfolio using advanced analytical techniques. INPUT: I will provide a list of my current stock holdings, including the ticker symbol, number of shares, and cost basis for each position. For example: NVDA, 100, $150 AMD, 200, $75 PLTR, 500, $15 AVGO, 50, $800 TSM, 300, $120 INSTRUCTIONS: Perform the following analyses for the provided portfolio, assuming a current date of January 1, 2026: 1. **Concentration Analysis**: Identify the top 5 largest positions by market value and their percentage contribution to the total portfolio value. Calculate the Herfindahl-Hirschman Index (HHI) for the portfolio to assess diversification. 2. **Sector and Factor Exposure**: Determine the primary GICS sectors and relevant investment factors (e.g., growth, value, momentum, size, quality) for each holding and the overall portfolio. Highlight any significant over or under-exposures compared to a broad market index like the S&P 500. 3. **Correlation Clusters**: Identify groups of stocks within the portfolio that exhibit high historical price correlation. Explain the implications of these clusters for portfolio risk. 4. **Drawdown Scenarios**: Model two hypothetical drawdown scenarios: a general market correction (-20% S&P 500) and a sector-specific downturn (e.g., -30% in the technology sector). Estimate the portfolio's potential value loss in each scenario. 5. **Tax-Lot Considerations**: For any positions showing significant unrealized gains, explain potential tax implications if sold, considering a [long-term capital gains tax rate] and [state tax rate]. Suggest strategies to manage capital gains if rebalancing. 6. **Rebalancing Plan**: Based on the analysis, propose a rebalancing plan to optimize for [desired risk level] and [investment objective, e.g., long-term growth]. This plan should include specific buy/sell recommendations (ticker, shares) and justify the changes. 7. **Performance Metrics**: Calculate key performance metrics such as portfolio beta, Sharpe ratio (assuming a [risk-free rate]), and Sortino ratio. 8. **Risk Attribution**: Attribute portfolio risk to specific holdings or sectors, identifying the largest contributors to overall portfolio volatility. 9. **Scenario Analysis (Custom)**: Analyze the portfolio's sensitivity to a [specific economic event, e.g., 100bps interest rate hike]. 10. **Future Outlook**: Provide a brief qualitative outlook for the portfolio's potential performance over the next 12-24 months, considering current market conditions and the identified exposures. FORMAT: Present your analysis in a structured, easy-to-read format with clear headings for each section. Use bullet points and tables where appropriate. Conclude with a concise summary of key findings and actionable recommendations.
10 prompts for how to use AI to analyze your stock portfolio
After providing your initial portfolio data, you can use specific prompts to drill down into various aspects of your holdings. These prompts allow you to explore different analytical angles, from risk assessment to strategic adjustments, ensuring a thorough review of your investment strategy.
1.
Portfolio Concentration
Analyze the provided portfolio for concentration risk. Identify the top 5 largest positions by market value and calculate their individual percentage contribution to the total portfolio. Additionally, compute the Herfindahl-Hirschman Index (HHI) for the portfolio to quantify its diversification level. Explain what the HHI value indicates about the portfolio's concentration.
2.
Sector & Factor Exposure
Determine the primary GICS sectors and relevant investment factors (e.g., growth, value, momentum, size, quality) for each holding (NVDA, AMD, PLTR, AVGO, TSM) and for the overall portfolio. Compare these exposures to a broad market index like the S&P 500 and highlight any significant over or under-exposures that could impact portfolio performance or risk.
3.
Correlation Clusters
Identify groups of stocks within the portfolio that exhibit high historical price correlation. For example, do NVDA and AMD show strong correlation? Explain the implications of these correlation clusters for the portfolio's overall risk profile, particularly during market downturns.
4.
Drawdown Scenarios
Model two hypothetical drawdown scenarios for the portfolio, assuming a current date of January 1, 2026: first, a general market correction where the S&P 500 drops by 20%; second, a sector-specific downturn where the technology sector (including NVDA, AMD, PLTR, AVGO, TSM) drops by 30%. Estimate the portfolio's potential value loss in each scenario.
5.
Tax-Lot Considerations
For any positions showing significant unrealized gains (e.g., NVDA if its current price is much higher than $150 cost basis), explain the potential tax implications if these positions were sold, assuming a [long-term capital gains tax rate] and [state tax rate]. Suggest strategies to manage capital gains efficiently if rebalancing is required.
6.
Rebalancing Plan
Based on the portfolio analysis, propose a rebalancing plan to optimize for a [desired risk level] and [investment objective, e.g., long-term growth]. This plan should include specific buy/sell recommendations (ticker, shares) for holdings like NVDA, AMD, PLTR, AVGO, TSM, and provide a clear justification for each proposed change.
7.
Performance Metrics
Calculate key performance metrics for the portfolio, including its overall beta, Sharpe ratio (assuming a [risk-free rate]), and Sortino ratio. Explain what each of these metrics indicates about the portfolio's risk-adjusted returns and downside protection.
8.
Risk Attribution
Attribute the portfolio's overall risk to specific holdings or sectors. Identify which individual stocks (e.g., NVDA, AMD, PLTR, AVGO, TSM) or sector exposures are the largest contributors to the portfolio's total volatility and explain why.
9.
Scenario Analysis (Custom)
Perform a custom scenario analysis: Analyze the portfolio's sensitivity to a [specific economic event, e.g., a 100 basis point interest rate hike]. Explain how such an event might impact the valuations and performance of the portfolio's holdings, particularly growth-oriented stocks like NVDA and PLTR.
10.
Future Outlook
Provide a brief qualitative outlook for the portfolio's potential performance over the next 12-24 months, assuming a current date of January 1, 2026. Consider current market conditions, the identified sector/factor exposures, and any specific trends relevant to holdings like NVDA, AMD, PLTR, AVGO, and TSM.
ChatGPT or Claude vs Fintwit
- ChatGPT and Claude offer structured, data-driven analysis, unlike the often anecdotal nature of Fintwit discussions.
- AI provides objective insights on concentration and sector exposure, while Fintwit opinions can be subjective.
- Chatbots generate specific rebalancing plans based on your data; Fintwit offers general market commentary.
- AI can simulate drawdown scenarios, a feature not typically available through Fintwit interactions.
- Dedicated platforms often provide live data feeds and screening tools, which chatbots currently lack.
| Feature | ChatGPT Plus ($20/mo) | Fintwit ($9/mo) |
|---|---|---|
| Real-time market data | No | Yes — live prices & signals |
| AI stock analysis | Manual prompts required | Automatic for any stock |
| AI portfolio health check | Not available | Built-in with recommendations |
| Curated AI stock picks | Not available | Daily AI top picks & ETFs |
| Stock screener | Not available | Full screener with filters |
| Trending stocks from X | Not available | Real-time signal extraction |
| Earnings & dividend calendar | Not available | Built-in calendars |
| Brokerage integration | Not available | Connect Robinhood, Schwab, etc. |
| Price | $20/mo | $9/mo |
Where ChatGPT or Claude falls short
- AI models do not have real-time market data access, relying on their last training cut-off.
- They cannot execute trades or directly integrate with brokerage accounts.
- AI may struggle with highly nuanced qualitative factors influencing specific stocks.
- The models lack predictive capabilities for future market movements or company-specific news.
- Complex tax optimization strategies beyond basic tax-lot considerations may exceed current AI capabilities.
Pro tips
- Always verify AI-generated insights with current market data and your own research.
- Break down complex requests into smaller, more manageable prompts for better accuracy.
- Specify your investment goals (e.g., growth, income, capital preservation) to tailor AI responses.
- Ask the AI to explain its reasoning for any recommendations or analyses.
- Experiment with different AI models (e.g., ChatGPT vs. Claude) to compare outputs and identify strengths.
Want this analysis on every stock you own?
Fintwit gives you AI stock analysis, real-time signals from X, and curated picks — built on the same data this post is grounded in.
Start Free Trial
Free to start. Premium just $9/mo — half the price of ChatGPT Plus.