[HN Gopher] Show HN: Pebble Finance - Personalize Your Investmen...
___________________________________________________________________
Show HN: Pebble Finance - Personalize Your Investments Today
Hello HN, We are Pebble Finance! Our newly launched product offers
a custom indexing solution, empowering investors to personalize
their investment portfolios. # The product _What our product is
now:_ We are creating a platform for users to use natural language
to search for their interests and personalize their portfolio.
Search is a combination of using OpenAI LLM models with Langchain,
OpenSearch index, and some traditional NLP techniques. Search is
divided into several tools which are selected based on the user's
input query. Based on the complexity of the input query, a single
tool or a combination of tools can be used to return a list of
companies for the user's portfolio. Also based on the complexity of
query search times can vary from less than a second to up to 15
seconds. _List of tools_ - Themes - General themes or concepts
such as type of company - Index/ETFs - Search for common ETFs such
as S&P 500, Russell1000, and Russell3000 Location - Currently we
can search for US states and countries (we are going to be adding
in US cities soon as well) - Fundamental Metrics - Filter
companies based on fundamental metrics such as market cap, revenue,
and pe ratio - Supplier Data - Identify companies based on their
supplier relationships _What we would like to add:_ We are
looking to add more tools to add more functionality for users. Some
tools we are looking to add are based around news integration,
historic stock price, and expanding our sources of data We are
also trying to improve search speed while keeping quality of
results consistent so we are looking at new ways to parse queries
such as with fine tuning transformer models and looking at more
traditional NLP techniques. _Challenges we have come across_ We
are seeing issues with trading off between speed and quality of
search results. Many of the queries can take up to 15 seconds based
on the complexity. Also saw issues where LLMs are producing
hallucinations which led to incorrect results. We have mitigated
this issue by using OpenAI's davinci-003 model versus gpt3.5-turbo,
but this also increases overall cost. _Some Example Queries_ - I
want to invest in eco friendly companies - Faang without the n -
Electric cars without elon musk - Californian companies - Aapl -
Top marketcap companies - ev companies with marketcap above 10
billion - s&p without apple # Feedback Please try out our search
capabilities on pebble.finance/themes and check the results! We
would really love honest feedback on search results, suggestions on
improving results/speed, future tools, and/or general thoughts!
Thanks for reading! The Pebble Finance Team
Author : jau-yeung
Score : 17 points
Date : 2023-07-27 19:00 UTC (4 hours ago)
(HTM) web link (pebble.finance)
(TXT) w3m dump (pebble.finance)
| ProjectArcturis wrote:
| Fundamentally, I don't understand the appeal of hooking up an LLM
| to answer investment queries. Who is your target audience?
| Someone who doesn't want to invest in index funds, but also can't
| be bothered to do more than 2 minutes of research?
| whitej125 wrote:
| Hey - one of the founders here. Great question!
|
| Wrt/ audience there are a lot of dimensions so to highlight
| some: * self-directed (vs fully managed) * values
| diversification (vs concentrated positions) * longer term buy-
| n-hold (vs yolo) * want their investments to incorporate a
| personal idea, need or value
|
| You're absolutely right that some types of inquiries might only
| be 2 minutes of research. At the same time... a lot isn't and
| people might not know where to start.
|
| If you wanted to find "cancer research companies" companies...
| there are hundreds. If you wanted "EVs but no Elon"... we'll
| help you broaden (diversify) that beyond just Rivian and Lucid.
|
| The initial "query" here is just the tip of the funnel when it
| comes to portfolio construction and ultimately its automated
| management. But that tip alone is a pretty fun demo to play
| with.
|
| Thanks for the feedback!
| ProjectArcturis wrote:
| I clicked the top button and got a 400 error.
| msadowski wrote:
| That's what I get trying to access it:
|
| 403 ERROR
|
| The request could not be satisfied.
|
| The Amazon CloudFront distribution is configured to block access
| from your country. We can't connect to the server for this app or
| website at this time. There might be too much traffic or a
| configuration error. Try again later, or contact the app or
| website owner. If you provide content to customers through
| CloudFront, you can find steps to troubleshoot and help prevent
| this error by reviewing the CloudFront documentation.
| jau-yeung wrote:
| Hello, we are looking into the issue! What country are you
| located in?
| msadowski wrote:
| I'm in Czech Republic
| jau-yeung wrote:
| we disabled geoblock so should work now. Please try again.
| Oras wrote:
| Same here
| sivers wrote:
| Same in New Zealand
| tedmiston wrote:
| Working fine from the US now.
| jau-yeung wrote:
| Please try again. Should work for all countries now.
| nborwankar wrote:
| HNb h h ub Ru CA and on. C. Draftyfrtrrs see some drawseseeees
|
| GCS r is z Aa
___________________________________________________________________
(page generated 2023-07-27 23:01 UTC)