Frequently Asked Questions

Common questions about the methodology, data, and what the score means.

What is FilingDrift? +
How do you compute the score? +
How is this different from asking ChatGPT? +
If the score is deterministic, why did it change since the last time I checked? +
How is this different from just reading the 10-K myself? +
Are all the validation numbers from the same dataset? +
How accurate is it? +
Are the backtest results statistically significant? +
Isn't the −22.4% just because your corpus is small-cap and the S&P 500 is dominated by mega-cap tech? +
SEC filings are public the moment they're filed. Why hasn't the market already priced this in? +
The backtest shows 41% of flags didn't underperform at 1 year — isn't that your false positive rate? +
What should I do when a company is flagged? +
What's the difference between semantic drift and sentiment analysis? +
Isn't this survivorship bias? You picked companies you already knew failed. +
Does the algorithm have lookahead bias? Did you tune it knowing the outcomes? +
Why does the backtest exclude 2007–2011? That's when most of the distress actually happened. +
If this tool is so accurate, why don't you trade on the signals yourselves? +
Is this investment advice? +
How often are scores updated? +
What companies are covered? +
What's in the Pro tier? +
I've been subscribed for months and haven't received any alerts. Is something wrong? +
Why did a company's score change even though its filing didn't? +
How does this compare to existing academic research on 10-K text analysis? +
Who is this for? +
You only analyze 10-Ks. What about 10-Qs, 8-Ks, earnings call transcripts? And global markets? +
Who built this? +

Have a question that's not here? Email us at hello@filingdrift.com.

This site uses a session cookie for authentication. We also use Plausible Analytics, a privacy-friendly, cookieless tool that collects no personal data and requires no consent under GDPR. See our Privacy Policy.