Experimenting with GPT-3: Building an Investment Analyst
We have been experimenting with using GPT3's reasoning capabilities to build an investment analyst that does this : (1) Summarize relevant news of the last 30 days, (2) Write a SWOT analysis, (3) Identify competitors, (4) Identify Key Risks, and (5) Write three investment theses (bull, neutral, bear) Here is an example how this can look like: https://app.finclout.io/tp/MSFT https://app.finclout.io/tp/LYFT https://app.finclout.io/tp/AAPL https://app.finclout.io/tp/UBER So far, the results of getting reliable data…
In plain words
This tool uses GPT-3 to generate automated investment analysis for public companies. It summarizes recent news from the past 30 days, conducts SWOT analysis, identifies competitors and key risks, and produces three investment theses representing bullish, neutral, and bearish perspectives. The tool is designed for investors seeking rapid, AI-generated fundamental analysis. While the system shows promise in generating useful summaries, the creator notes that API rate limits present operational challenges despite paid usage.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
We have been experimenting with using GPT3's reasoning capabilities to build an investment analyst that does this : (1) Summarize relevant news of the last 30 days, (2) Write a SWOT analysis, (3) Identify competitors, (4) Identify Key Risks, and (5) Write three investment theses (bull, neutral, bear) Here is an example how this can look like: https://app.finclout.io/tp/MSFT https://app.finclout.io/tp/LYFT https://app.finclout.io/tp/AAPL https://app.finclout.io/tp/UBER So far, the results of getting reliable data back through well-engineered prompts through the API is quite promising. Yet, from an operational perspective, the biggest problem is that even though we are not using the free service but pay for it frequently run into rate limits. Positives: For Apple, the News Summary provided a useful result. "Apple Inc. is launching Apple Pay Later soon to revolutionize the buy now, pay later (BNPL) industry. Its stock is currently indicating a potential move to $167. The company is also facing an investigation by the Pomerantz Law Firm on behalf of iPhone 7 owners who experienced performance degradation following a device update. Apple's latest iPhones are being sold at discounts in China and the company is expected to rollout a high-end iPhone 'Ultra' in 2024. Additionally, two top market watchers discussed tech's wild run this year." For Microsoft, the Bull-case made more sense than the Bear-case Bull-case "Microsoft Corporation is a technology leader in the industry and is well-positioned to benefit from the increasing demand for cloud computing and artificial intelligence. The company's strong balance sheet, competitive advantages, and focus on innovation make it an attractive long-term investment Bear-case "Microsoft Corporation is a large, mature company with limited growth potential. The company is facing increasing competition from smaller, more nimble competitors and is struggling to keep up with the rapid pace of technological change. Investors should b e wary of investing in Microsoft due to its lack of innovation and potential for declining market share." Negatives: GPT3 is only guessing the next best word. Which might sometimes provide strange results. For example, considering the News Summary for Uber "Uber Technologies, Inc. reported a surge in fourth-quarter revenues and a strong outlook for 2021." We are not in 2021 anymore for a long while. Clearly, GPT3's knowledge of the Yahoo finance dataset has been cut off in 2021 and applied the provided news effectively. For AAPL, GPT3 did not identify any competitors. While we could argue that HP, MSFT, or similar hardware+software companies are in fact, competitors. In conclusion, we need to further investigate if the actual reasoning of GPT3 is mature enough to provide a useful analysis of the stock. Especially under liability considerations. Yet, if it works it could be a really powerful game-changer. Clearly, that is only an experiment and shouldn't be used as an investment recommendation nor seen as investment advice in any way.
Does the same job
all alternatives →
Stock Market GPT for Investment Research2024 · ▲127AI powered stocks, balance sheets, analyst report comparison
- G3GPT-3 resources, examples, and use cases2021 · gpt3demo.com · ▲19
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
