Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

news.ycombinator.com

Post reply on HN
Print view View original

71–80 of 109 posts

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#71

Post by hogFeast »

kbennatti wrote: post #65
htrp wrote: post #47

Earlier quoted context omitted.

Realistically they probably don't need to do that. The filings are usually pretty heavily lawyered up and the lawyers are pretty lazy on language updates.

Yeah, people have been doing sentiment analysis of press releases etc for years now and very few corporates bother trying to use software to test/counteract it

Companies are already doing this. IR consultants have, allegedly, been advising exec teams to use/not use certain words based on their impact on AI models. It is inevitable.

SEC filings are somewhat more robust because they are a standardized format but the point of many of these frauds, for example SinoForest, was about things which weren't in the document not the things that were (the stuff that was in documents was never a smoking gun...iirc, I remember looking at the stock before it happened...a lot of these Chinese frauds had totally fine numbers though, that was the point).

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#72

Post by polpenn »

Great work! I work in financial services and built a similar tool for sentiment analysis and topic modelling on transcribed earnings calls. The idea was to identify topics at a speaker-level (analyst, management, etc.) and evaluate the sentiment around that topic. For example, perhaps "foreign exchange" was discussed negatively by a given company in an earnings call, which would alert the analyst to review that call in greater detail.

Are you guys thinking about incorporating something like this into your product?

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#73

Post by piesauce »

polpenn wrote: post #72

Great work! I work in financial services and built a similar tool for sentiment analysis and topic modelling on transcribed earnings calls. The idea was to identify topics at a speaker-level (analyst, management, etc.) and evaluate the sentiment around that topic. For example, perhaps "foreign exchange" was discussed negatively by a given company in an earnings call, which would alert the analyst to review that call…

Thanks! Earnings transcripts sentiment analysis is not currently in our product roadmap. One of the reasons is that such tools are already available on the market. We wanted to explore more underutilized sources of information.

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#74

Post by HeatherJudd »

shum1 wrote: post #70

As someone who has looked into alternative data business models for the finance industry, this is really awesome to see someone doing this as a company. I was interested to understand how you think about your revenue model? I feel that if your data provides alpha (i.e. selling before other people are aware of the problematic disclosures), as your models become validated within the industry, someone/some firm is going…

It's definitely something we've discussed as a team. We would like to help make fraud less profitable.

The current iteration of the product requires users with some level of financial expertise - hence why we are starting with fundamentals investors. We believe that the longer a fraud goes on, the more people get hurt - so we want to bring these issue to the forefront. Perhaps each trade can be considered a zero-sum game, but long-term there is a benefit to all market participants. We love the idea of every investor considering how aggressive accounting/reporting informs management integrity. Unfortunately, I think we have some time before this becomes the norm.

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#75

Post by jpkotyla »

Quant with some NLP experience here. Impressive business traction so quickly, good stuff. Who do you see as competitors in this space? I'm wondering whether you think that footnoted* (https://footnoted.com) offers something similar, or might your products be complimentary in some way? Thanks.

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#76

Post by kbennatti »

jpkotyla wrote: post #75

Quant with some NLP experience here. Impressive business traction so quickly, good stuff. Who do you see as competitors in this space? I'm wondering whether you think that footnoted* ( https://footnoted.com ) offers something similar, or might your products be complimentary in some way? Thanks.

We love footnoted! Michelle Leder of footnoted has been really supportive of our work. She recognizes that it's an important area for tech innovation. footnoted isn't operating right now but when it comes back, we'll support her and collaborate if we can.

We're often compared to AlphaSense, Sentieo and InsiderScore but our product is pretty different. Competitor products focus on sentiment and linguistic metrics or search etc, not on extracting and organizing important textual content.

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#79

Post by soheil »

It seems to me all you have to do to fool a ML model is rephrase sentences and just use verbiage it has never seen before. So why isn't your tool just the latest item on a pre-IPO company's checklist that is looking to commit fraud to scrub against?

Also if Muddy Waters can do something similar to this (if not better?) doesn't that mean you should just hire them and throw away your ML model?

Re: Launch HN: Bedrock AI (YC S21) – Using ML to identify red flags in SEC filings

#80

Post by soheil »

danielmarkbruce wrote: post #77

Out of interest - why didn't you start a hedge fund instead?

I think big part of a strategy like this is long term. If you want to short a stock you need to make sure the fraud is discovered by other investors. So you probably need to have a strong marketing department that basically thrashes other companies, this may not be a goal a lot of people aspire to. With a short you're also exposed to lose an infinite amount.

And finally "markets can stay irrational longer than you can stay solvent." -Keynes

Post reply on HN