Feedback on stock analysis platform
Hello folks,
I'm working on a project to use AI to help interpreting technical indicators (combining daily, weekly and monthly timeframes), fundamental data (like EBITDA, EPS, P/E etc), risk models and news.
The idea is to link all this information using AI and present that to you in a way that saves you time and saves you brain power for other tasks, and of course you can ask questions on demand.
I've created this website and social media yesterday, please give me some feedback. Since I'm just a software engineer with a passion for finance, you guys who are on the battleground everyday may provide more valuable insights.
Edit: I still can't post links, but the tool is called llastro dot com
the ai slop thickens
Based on the most helpful WSO content, here are some insights and feedback for your stock analysis platform idea:
Integration of AI in Finance:
User Experience:
Timeframe Analysis:
On-Demand Questions:
Target Audience:
Marketing and Feedback:
Potential Challenges:
Your project has potential, especially if it can genuinely save time and provide actionable insights. Keep refining it based on user feedback and stay transparent about what the platform can and cannot do. Good luck with llastro!
Sources: AI in fundamental investing, How To Follow The Markets Like A Pro – For Free!, Review My Stock Pitch, Feedback on Stock-Pitch., How To Follow The Markets Like A Pro – For Free!
I've been investigating this space for a little bit, and I have to say: there's a lot of thought that goes into how LLMs interpret questions for those in the finance community.
For instance, say you ask a question "How is AAPL doing?"
Well, depending on whether you're: a wealth manager, investment banker, corporate banker, or asset manager, you may very well be asking four different questions.
Wealth Managers may be asking about period performance metrics such as percent change, WTD %, MTD % and YTD %, investment bankers may want a summary of their latest earnings and any significant developments to be aware of, corporate bankers may be most concerned with their cashflows and paying capacity, and asset managers may be looking at risk-adjusted return metrics or return over a benchmark.
Now if the LLM is designed to interpret the question with the retail investor or wealth manager in mind, they'd just give the standard period performance stats, but if it could have the context and retain the context for the given user, then you could interpret any and all questions in the context of a given persona.
When we add the complexity of ratios, we get into sanitized/standardized ratios that may or may not conform to the methodology the given user is considering. For instance, P/Earnings - is it considering yesterday's close, 15 minute delayed, or real-time price? For Earnings, is it considered TTM using past four quarters? How are one-time line items considered? Maybe just FY statistics? Can it view three year average? How is a peer group decided? What if the peer group is inaccurate given that it may just tie to a given economic sector?
The more you dive into the details, the more you need to build out the solution to interpret and provide a whitebox of calculation methodologies or have the audit capability. If you're advocating for maintaining the raw data with minimal changes, then it would preserve the data, but perhaps not align to the investment banker's interpretation of what may be considered as part of the ratio calculation.
All the big players are looking to solve this problem of how text should be interpreted and what constitutes relevance as well as how best to present information from an LLM, but I havne't seen any LLM really out-solve the issue against their competitors.
Est atque ad explicabo ut facilis nesciunt animi. Quia molestiae quas voluptatem sit aut qui. In maiores quia aspernatur eum officia.
Ipsam reiciendis odit et et aut porro cum. Hic animi est doloremque est vel velit. Totam eius voluptas sit accusantium commodi ducimus. Iste expedita quaerat quia id aliquid.
See All Comments - 100% Free
WSO depends on everyone being able to pitch in when they know something. Unlock with your email and get bonus: 6 financial modeling lessons free ($199 value)
or Unlock with your social account...