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 real time 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 out consistent alpha in the dangerous world of micro-cap stocks? Lets find out.
Overview
This was yet another staggering week for ChatGPT. Despite facing a downturn on Monday, the growth the following days was unstoppable. Investing profits from Candel Therapeutics Inc. (CADL) into Actuate Therapeutics, Inc. (ACTU) was genius, capturing a 27.37% rise. It’s other stocks however, were unimpressive. Azitra Inc (AZTR) continued to bleed cash and Inspira Technologies (IINN) had a slight gain of 3%.
Performance Graph
Portfolio Review
To see the full report: Click Here
Here was this week’s revaluation summary:
Rationale & Conclusion
This rebalance aggressively reallocates capital toward the highest-upside opportunities while exiting a clear laggard. The strategy effectively trims profits (Inspira), cuts dead-weight (Azitra), and seizes two timely, catalyst-driven trades.
New Additions:
Axogen (AXGN):
Near-term binary FDA decision (~6 weeks) for Avance, backed by an already profitable-growth model. Potential for a fast spike if approved, with downside cushioned by ongoing revenue.Esperion (ESPR):
Turnaround cardiovascular story with real revenue growth and multiple quarters of cash runway. Risk/reward skews positive — if profitability or strategic news hits, a double is plausible. Diversifies the portfolio beyond devices/rare diseases.
Key Holdings Retained:
Abeona (ABEO):
De-risked biotech with FDA-approved product (ZEVASKYN) launching now. Cash-rich and positioned for alpha as sales come in.Inspira Technologies (IINN):
Riding momentum from major contracts and Nasdaq compliance. Trimmed for profits, but strong catalysts remain — continued upside likely.Actuate Therapeutics (ACTU):
High-risk/high-reward oncology play with excellent data and strong investor backing. Stop-loss protects downside; upside could be a multi-bagger.
Risk & Strategy Notes:
AZTR exited due to weak near-term outlook and high dilution risk.
AXGN and ESPR added for event-driven setups (FDA approval, profitability inflection).
Position sizing remains disciplined — no over-concentration, all trades are full-share and within cash means.
Stop-losses enforced to protect downside; failed trades will self-limit risk.
Final Thoughts:
This reallocation sets the portfolio up for a high-alpha second half of 2025. We’re now concentrated in positions with:
Clear upcoming catalysts
Positive news flow or earnings momentum
Institutional or insider alignment
The new mix reflects a focused, evidence-backed, and risk-aware approach — fully aligned with the project’s mission to see if LLM-guided portfolios can consistently generate alpha in volatile micro-cap territory.
My Thoughts
Edit: Because AXGN was way above $7, it decided to just put the capital into ESPR (for a position of 20 shares).
I like the idea of finally cutting off Azitra (AZTR), however I think it’s mostly because the new chat wants to restructure. I am a worried that it will lose conviction with the new picks and won’t wait for the event-setups. Also, I fed it PnL data for all tickers and IINN doesn’t have profits? So I’m unsure where it got that idea, but I’ll tell it before I put in the trades. Can it maintain this level of growth? Subscribe and find out next week!
GitHub Page and Email:
To see past deep research reports and summaries: Click Here
Have a question? Check out: Q&A
If you’re curious about the code I’m using to automate results and graph, the GitHub page is: ChatGPT-Micro-Cap-Experiment
If you have any suggestions or advice, my Gmail is : nathanbsmith729@gmail.com
Have you tried to run backest on years historical data, accounting llm model's cut off dates?