Show HN: Left Nvidia to build an AI Investing Copilot. [Need Feedback] | Hacker News Reader

Show HN: Left Nvidia to build an AI Investing Copilot. [Need Feedback]

rafa.ai

13 pointsabsinha20 comments

Would love to test it, but I am not willing to leave my payment details. I understand the need for conversion but if you are confident about your product and its standing against competition (haven't seen anything like Rafa yet), why not offer a true free trial phase without subsequent subscription?

So it is paradox to write in your FAQs "Yes, RAFA offers a 14-day free trial allowing you to explore its features and determine if it's the right investment tool for you before committing to a subscription." -> READ: before committing to a subscription

"Democratising intelligent investing, together." would mean (at least to me) you lower the entry point.

Send a mail to support@rafa.ai and lets get you a pass to try it :-)

I would be interested in the 14 days free trial too, but either put it on the website for everyone or remove any mentions to it.

Our 14-day trial on the web operates similarly to systems like iOS or Android, allowing users to cancel their subscription at any time during the trial period without incurring charges. However, we do require users to provide a card on file as a precaution against potential system abuse.

Hey HN,

Four years ago, I left my comfortable AI engineer job at NVIDIA to chase a dream: making intelligent investing accessible to everyone, not just Wall Street hotshots.

As a busy professional myself, I was frustrated with the existing investment tools. They felt clunky, lacked actionable insights, and seemed more focused on generating trading fees than helping me succeed.

I craved a tool that acted like a 24/7 personal analyst, constantly monitoring the markets and my portfolio, and offering data-driven insights to guide my decisions.

I knew I wasn't alone. Many investors struggle to find an edge in the market, often relying on gut feeling or trending news instead of solid research and analysis. I envisioned a world where everyone could have access to the same level of expertise and insights as the pros, without the hefty price tag.

Rafa.ai leverages the power of LLMs and advanced quantitative models to provide personalized, actionable investment insights. It's like having your own team of expert analysts, constantly monitoring the markets and your portfolio, and offering guidance tailored to your unique goals and risk tolerance.

We don't profit from your trades; our mission is to democratize intelligent investing and empower individuals to take control of their financial future.

With Rafa.ai, you can:

Reclaim your time: Spend less time analyzing and more time living your life, knowing your investments are in good hands.

Make informed decisions: Gain access to deep, data-driven insights into market trends and your portfolio's health.

Enjoy a personalized experience: Rafa.ai tailors its analysis and recommendations to your unique investment profile.

Manage risk effectively: Understand and mitigate potential risks in your investment strategy.

Continuously learn and grow: Enhance your financial literacy and investment skills with expert advice and insights.

I believe financial freedom shouldn't be a luxury reserved for the wealthy. Rafa.ai combines cutting-edge technology with a user-friendly interface to make intelligent investing accessible and affordable for everyone.

I invite the HN community to try Rafa.ai and share your feedback. Your insights will help us shape the future of investing.

Let's democratize intelligent investing, together.,

Abhinav Founder, Rafa.ai

An LLM makes no sense to me in this use case. I don't know shit about investing, but machine learning has a place in analytics, but llms are about finding correlation in text. When I'm dealing with images, I use a convolutional nn, not an llm. Developing a finance model makes a ton of sense to me, but not as an llm. LLM can't even do math without writing code to do it.

I guess you see something I don't, which is not unprecedented. I miss lots.

We are not using LLMs to replace the existing set of proven Machine Learning (ML) methods for extracting financial insights. Instead, LLMs play a key role in our system. They help reduce data overload and tailor the responses to the specific information an investor needs.

Consider a Bloomberg terminal - professional investors often spend days setting up their dashboards to see the right insights. With our system, investors can simply send natural language queries, and the LLMs act as a "glue layer" between the investor and the sophisticated quantitative models running behind the scenes.

Another major use case is screening. Traditional screening tools can be cumbersome, with hundreds of buttons and drop-downs. LLMs allow us to make the screening process more natural by generating the right queries from simple user questions. This is a more powerful approach.

In the past, sentiment analysis was challenging, requiring complex Named Entity Recognition, classification, and summarization models. Even basic 7 billion parameter LLMs now outperform hand-built classifiers for tasks like news sentiment analysis and SEC filings summarization.

In summary, our system is not just based on LLMs. It is a comprehensive solution that uses LLMs as a key component, alongside other essential parts like data ingestion pipelines and sophisticated quantitative models. The LLMs serve as an intuitive interface, allowing investors to access the power of the underlying financial analytics and lower the barrier to entries for all investors alike.

The LLM is used to power an interface that allows users to easily query and consume insights. It’s not what generates the insights.

* I’ve been working on the UI/UX of RAFA. Any feedback would be welcome.

I just got back from trying Rafa. It seems very promising. I was relying on a CustomGPT for getting stock info but for some reason, it wasn't that great. I now rely on my friend's brother. I just copy whatever he does. Maybe I will try doing my analysis with this app for a change

Amazing, will look forward to seeing how you beat the benchmarks with this :-)

It says you use plaid to access portfolio data, but what does this typically leverage under the hood? Oauth or similar APIs or user/pass + screen scrapping?

Is there an option to manually populate your portfolio?

Plaid uses oauth for many institutions like Robinhood. We currently do not have an option for manual portfolio entries.

Interesting project! Many people face the problem and look up for general advice. Copilot seems to be the best interface, in my opinion, to get started investing and gradually dive deeper into it.

Totally! It's a great way to get the basics before meeting with a financial advisor. Some even see it as a handy alternative :-)

Your pricing page says 14 day trial, but when I entered my credit card it charged me. This is fraudulent behavior.

Was this on the web or android? Please contact us at support@rafa.ai and we will immediately look into it

Thank you for your reply. It happens on the web platform.

what are the sources for your RAG? fintwitter?

Sources : SEC Filings, Transformed Company fundamentals, Price / Volume Data, Crypto, OPRA 15min delayed Options data, Realtime News and our internal quants

excellent product

Reply on news.ycombinator.com