This is cool!<p>We've been working on something similar, but the opposite direction (for world trade data). Instead of trying to NLP our way out of the problem, we pre-generate and index a bunch of possible questions, and let full text search handle the rest.<p>It's interesting, because theoretically NLP should be able to "understand" what you mean but in reality I find that even if you parse sentence structure and extract some meaning, you're still at some level hardcoding the possible things that can be queried into the code.<p>So it's a neat tradeoff of whether it's more worth it to create a mini query language, or go full natural language, or go somewhere in between.<p>...<p>Anyway, try it out by clicking on the title (keeping it a bit hidden for now for testing purposes): <a href="http://atlas.cid.harvard.edu/explore/tree_map/export/usa/all/show/2012/" rel="nofollow">http://atlas.cid.harvard.edu/explore/tree_map/export/usa/all...</a><p>Things you can try (mix and match too!):<p>- "wine italy"
- "france"
- "germany spain"
- "germany export wine 2002 to 2012"
- "turkey feasible"<p>...<p>If you want to see the code, check out our github:<p><a href="https://github.com/cid-harvard/atlas-economic-complexity/blob/master/django_files/observatory/views_search.py" rel="nofollow">https://github.com/cid-harvard/atlas-economic-complexity/blo...</a> (search view)<p><a href="https://github.com/cid-harvard/atlas-economic-complexity/blob/master/django_files/observatory/management/commands/index_questions.py" rel="nofollow">https://github.com/cid-harvard/atlas-economic-complexity/blo...</a> (indexer)<p>Apologies for any mess, I recently joined and we're undergoing a huge overhaul right now.
Congratulations on launching! Cool idea and a good start. I think since you're targeting the non-professional market here, you need to focus on user experience a bit. Some feedback:<p>- Found it a bit slow, but guess that's partially the HN effect.<p>- As per above, I'd make the queries ajax rather than refreshing the whole page every search, should improve the UX a fair bit.<p>- I expected autopredict when I started to type $... to predict a ticker, would be nice to guess company names as well if no ticker is entered. Probably an essential feature for non-pros.<p>- You need a clear signup link. And the redirect when you run out of free credits should go to the signup page with small link to login, not the other way around.<p>- Also look at highcharts.com, they have a stock chart product as well. Hands down the best JS charts, mobile friendly, highly customisable etc.
It's a pity you have to specify a ticker. I was really hoping it can do the hard work for me.<p><a href="https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%93&query=find+me+best+investment+in+2014&button=" rel="nofollow">https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%9...</a>
Congrats! Looks good!<p>Small issue: you're calling Google fonts over HTTP, but your site uses HTTPS, so Chrome is blocking the request. This leads to your fonts rendering in the default (Times New Roman here).<p>[blocked] The page at '<a href="https://www.pennywhale.com/'" rel="nofollow">https://www.pennywhale.com/'</a> was loaded over HTTPS, but ran insecure content from '<a href="http://fonts.googleapis.com/css?family=Montserrat:400,700'" rel="nofollow">http://fonts.googleapis.com/css?family=Montserrat:400,700'</a>: this content should also be loaded over HTTPS.
Honest feedback from a quant working for an asset manager: This is not (yet) useful. None of these queries even come close to being a real question a financial researcher would ask.<p>What's a real question like? here are examples which your system doesn't even try to handle.<p>* companies in S&P500 with P/E less than 15<p>* companies in S&P500 with more than 20% of their revenue coming from China<p>* $TSLA Beta with technology sector (returns the wrong answer).<p>* <a href="https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%93&query=%24TSLA+beta+with+%24AAPL&button=" rel="nofollow">https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%9...</a> (this produced a serious error on your server)<p>If you want to answer trivial questions your product will fail. nothing you've done isn't done better by Google RIGHT NOW.<p>Not trying to discourage you but this just doesn't solve any existing problem. All you have is a pretty interface to a tool that does one thing poorly.<p>If you can actually solve 15% of the real problem with converting natural language questions into financial queries and return accurate, well formatted data, you will have a serious product. Right now you are nowhere close.
Pretty interesting effort, but a bit of constructive criticism:<p>- none of your query results have a date attached! While pretty, an earnings number without a date is like a chart without an axis.<p>- Just how natural can the queries be? "$AAPL sales estimates" did not return anything. Neither did "$CAT cost of capital". "quarterly $CAT earnings growth" gave me a single EBIDTA number", e.g. not what asked. Is it easier to start with simple dropdowns?<p>- Why the stocktwits $ prefix? Why cant a company name be used?<p>- Another "sad face" feature - every not found/no results query takes away a "free query" :(<p>On more positive note, things look really clean - good job on the design! A great start. Is the long-term idea here to build an accessible place for fundamental data research?<p>What value added are you providing in your premium product (aside from heatmap) over just going over to EDGAR archive?<p>Ping me directly - would love to provide more feedback!<p>Edit: fix formatting :)
Hey Jay,<p>This is really cool. One idea is it would be great if you could interface with EDGAR and gather the links to the various financial statements. The EDGAR database search/navigation is horrendous.<p>As another commenter said, it would be great if it could detect the company name or at least the ticker without the $.<p>Also, a failed query subtracts from the guest query allotment. That doesn't seem ideal as I'm first learning how to phrase my requests.<p>Lastly, mutual fund data would be awesome. Morning star rating, fund performance, fund assets, etc.
This is pretty great. I am convinced there is lots of room in this space for services that cater to people who aren't quite in the Bloomberg terminal crowd, and yet would benefit from easy access to financial data for whatever reason. I've been working on a service to open up EDGAR data to more people: www.easyedgar.com (pre-launch). Not quite as fancy as Penny Whale but I think a lot of people just want the data in their spreadsheet and don't know how to do that.
This is intriguing. Large implications when applied to private datasets ---- think Factiva, etc. There the data schema differ so wildly that natural language can really make it more useful. Publicly traded equities is the facile, simple place to start, obviously.<p>Can I spin off a search and get pinged on updates?<p>Love to learn more.
It's slow to load at the moment, so I'll describe what it does.<p>PennyWhale lets you search, manipulate, and compare financial data with natural language queries along the lines of "how much cash does $GOOG have" and "show me the PE ratio for $AAPL".<p>Seems like a really good research tool!
I suggest including parameters mentioned in the book "The intelligent investor" praised by Buffet. For example, the earnings in last 20 years, total value of tangible assets, etc. Company information on value investing are hard to find, and this could be a great help.
I didnt get any results for this query:
<a href="https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%93&query=%24tsla+sales+growth&button=" rel="nofollow">https://www.pennywhale.com/app/queries/execute?utf8=%E2%9C%9...</a>
Neat. I can see myself using this.<p>Two bugs: "$brkb book value per share" gives a number that's way off. "$brk.a book value per share" and "$_x EV/EBITDA" yield apparent server side errors.
When I tried the query:
"show me the ratio of $SLV vs $GLD"<p>I get:<p>"We're sorry, but something went wrong.<p>If you are the application owner check the logs for more information."<p>Is this due to the usual HN overload? or did I hit a bad spot?<p>This looks extremely interesting!
How do you guys plan to compete with Google Spreadsheets?<p>I can already do this stuff in it (free) and just use the built in GoogleFinance calls (and their limit is 1000 per sheet).<p>Plus I have all the other advantages of a spreadsheet program.
How does this compare to Bloomberg?<p>From what I've seen, people in the financial services industry have gotten very good at using the Bloomberg Terminal commands to examine this kind of data.
Searching for "pe ratio for google" in pennywhale doesn't return anything, while the same query in google actually returns the PE ratio for GOOG.
not sure if this is the right place to report bugs (and/or if this is intended behavior), but if one clicks the COMPUTE button without a query entered, it decrements the guest query counter