Recap
Hey guys! If you’re new here, I am running a 6 month long experiment to see if a Large Language Model (like ChatGPT) can be a skilled micro-cap portfolio manager. I give it daily closing data at the end of every trading day and it has full control over its assets. Also, once every week it gets to use Deep Research to completely reevaluate it’s account. Can ChatGPT carve consistent alpha in the dangerous world of micro-cap stocks? Lets find out.
Overview
Merry Christmas! Hope you all are enjoying the holidays.
Before we get started, I would like to thank you guys. I would have never imagined the support I have gotten over the past six months. It’s definitely been a journey, and you guys have allowed me to grow in both technical skill and consistency. I’m sure I’ve said this plenty of times, but I want you guys to know this is just the beginning.
Now, let’s get to the results.
The last week was pretty underwhelming, when no moves being made a little overall volatility. Unfortunately, the new add JSPR was not the saving grace ChatGPT had hoped for, with the stock moving down ~4% in the past week. SLS had a massive 20% move and MIST drifted down 1%. The final account balance is $82.88.
Performance Graph
Final Metrics
[ Risk & Return ]
Max Drawdown: -50.33% on 2025-11-06
Sharpe Ratio (period): -0.4321
Sharpe Ratio (annualized): -0.2429
Sortino Ratio (period): -0.5046
Sortino Ratio (annualized): -0.2836
[ CAPM vs Benchmarks ]
Beta (daily) vs ^GSPC: 1.1330
Alpha (annualized) vs ^GSPC: -34.31%
R² (fit quality): 0.027 Obs: 124
Note: Short sample and/or low R² — alpha/beta may be unstable.
[ Snapshot ]
Latest ChatGPT Equity: $ 82.88
$100.0 in S&P 500 (same window): $ 111.68
Cash Balance: $ 4.21
Ending Portfolio
ticker shares buy price cost basis stop loss PnL
MIST 14.0 1.75 24.50 1.8 4.62
SLS 5.0 1.41 7.05 1.1 7.30
JSPR 20.0 1.88 37.60 1.5 -2.40
Future Plans
The final, full in-depth report will likely take a few weeks, with the scope and quality I’m aiming for. To be honest, I haven’t even started on the wrting, but I will keep all updates posted on X.
I have finally decided on a universe of stocks for the next experiment, and I have decided to go with new IPOs listed within the last 5 years. This was a great viewer suggestion, and I think this perfectly encapsulates high risk high reward companies without risking everything in game of chance.
On Saturday, I officially created Version 1 of my benchmarking project! All bugs I found during initial testing have been patched. Long term testing starts today, and I’m confident all the major changes have been implemented. The vision of the project has drifted slightly, but I think the new direction is far more important and less explored in the LLM trading ecosystem.
Stay tuned on X for more dev and updates!
External Links
To see all past deep research reports and summaries: Here
Full chats: Here
Have a question? Check out: Q&A
If you’d like to see the raw logs and full portfolio simulation code: GitHub Page
My X account: NathanS729
If you have any suggestions or advice, my Gmail is: [email protected]
Disclaimer
This project is purely educational and research-focused. Nothing here should be taken as financial advice. Full disclaimer: Here