61–70 of 109 posts
One thing I noticed about "Efficient Market Theory" is that it is unfalsifiable. It isn't a scientific theory and it also cannot be proved true or false, only useful when convenient. It relies on magic, rationality, and the assumption of omniscience by large investment banks.
Nothing is priced in.
> For example, our research shows it can take 12-18 months for corporate malfeasance to be incorporated into stock price after clear warning signs appear in financial text. One thing I noticed about "Efficient Market Theory" is that it is unfalsifiable. It isn't a scientific theory and it also cannot be proved true or false, only useful when convenient. It relies on magic, rationality, and the assumption of omniscien…
Given your example boilerplate disclosure, is one of your key conditional statements simply categorizing boilerplate? Like instead of simply putting a sentiment score on the wording, you first isolate it as boilerplate or as a unique potential aberration and then assign weights?
How would you address would-be filers from using your own product from iterating on their wording until the red flags are removed?
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.
Congratulations! I played with that database in 2017 when they opened up the text. I'm so happy to see it's finally been picked up. I built a thing which recreated the Income statements and then flagged for non-conformance. I found Babcock & Wilcox Enterprises "Good will impairment charges" as an anomalous line in their Nov 8, 2017 filing just prior to when their CEO resigned in 2018 and they had to make so many adju…
Do you consider validating financial figures against Benford’s Law distribution? Whilst it is not NLP I am curious does it still work?
Congratulations! I played with that database in 2017 when they opened up the text. I'm so happy to see it's finally been picked up. I built a thing which recreated the Income statements and then flagged for non-conformance. I found Babcock & Wilcox Enterprises "Good will impairment charges" as an anomalous line in their Nov 8, 2017 filing just prior to when their CEO resigned in 2018 and they had to make so many adju…
Which database?
Given your example boilerplate disclosure, is one of your key conditional statements simply categorizing boilerplate? Like instead of simply putting a sentiment score on the wording, you first isolate it as boilerplate or as a unique potential aberration and then assign weights?
You've hit the nail on the head (mostly)...but I'm going to say no more because its part of our secret sauce
An additional tool I always wanted was to match external - even macroeconomic - events to company risk factors
How do you balance those two sides? I mean it as a potential customer who would love to pay for your product, but want to understand how you prevent this becoming a alpha-generating NLP strategy for one hedge firm who pays the most for it.