About — FilingDrift

What this is

FilingDrift is a language-change scoring tool for SEC 10-K annual filings. It answers one question: does this year's filing say something meaningfully different from last year's — and if so, is that unusual compared to peers?

We built it because corporate distress has a pre-crisis signature in language. CFOs don't suddenly say "we're in trouble" — they gradually introduce hedging language, new risk factor categories, and liquidity disclosures that weren't there before. The change is subtle. The accumulation is not.

SVB's 2022 10-K scored 53.1 on our scale. The 95th percentile of healthy companies in our corpus is 44.0. The FDIC arrived 14 days after filing.

What this is not

Not investment advice. We score language. We don't predict price movements, recommend positions, or guarantee outcomes.
Not a crystal ball. 8 of 10 tracked crisis companies exceeded the control ceiling before their collapse. 2 did not. We're transparent about both.
Not a financial advisory service. Latent Systems SAS is a software company. We are not registered investment advisors, broker-dealers, or credit rating agencies.
Not affiliated with the SEC. We use publicly available data from EDGAR. We have no relationship with the SEC or any regulatory body.

How the score works

The distress score measures two things simultaneously:

What's new or escalating. Phrases that appeared for the first time, or dramatically increased, weighted by how rarely other companies use them. A phrase that only SVB was saying in 2022, that it hadn't mentioned before, scores higher than boilerplate that every bank uses.
Where the language is heading. We measure how the current year's language has shifted from last year, in the sections most predictive of distress — risk factors, liquidity disclosures, MD&A. This catches the drift that keyword lists miss.

Both are calibrated against a baseline of 30 healthy companies with no verified distress events. The 95th percentile of that baseline is the control ceiling — scores above it are flagged.

The algorithm is deterministic: no AI generation, no prompting, no summarization. The same filing always produces the same score.

See the full FAQ →

Detection results

The table below shows how the score performed against every crisis and control company in our corpus. We don't cherry-pick examples.

83%

Recall among companies with
2+ years of filing history

677 days

Average lead time before
crisis event (detected companies)

Company	Event	Peak score	Lead time	Result
PRTY (Party City)	Bankruptcy 2023	99.3	3.1 years	Detected
NKLA (Nikola)	Bankruptcy 2023	116.3	3.7 years	Detected
BBBY (Bed Bath)	Bankruptcy 2023	137.4	2.0 years	Detected
RITEAID	Bankruptcy 2023	79.0	167 days	Detected
SVB Financial	Bank collapse 2023	53.2	14 days	Detected
SI (Silvergate)	Liquidation 2023	18.9	—	Missed
CFC, REVLON, PCG, CHKAQ	Various	<6	—	No data †

† CFC (Countrywide, 2008), REVLON, PCG (PG&E, 2019), and CHKAQ (Chesapeake, 2020) have 0–1 filing pairs in our corpus — insufficient history to compute a meaningful drift score. We count them as misses to avoid cherry-picking. The score requires at least two consecutive filings to measure change.

False positives: 6 of 30 stable reference companies generated above-ceiling scores at some point. Four of the six occurred during the COVID disruption years (2020–2021), when market-wide language shifts reduced the specificity of peer normalization. One (RTX) followed a major corporate merger that produced large language changes for structural reasons.

We're expanding the corpus to improve statistical power. Current results are based on 44 as the control ceiling.

Known limitations (we'd rather tell you)

M&A distortions. When a company acquires another and consolidates filings, the combined entity may show language change that reflects the target's pre-existing disclosure style, not a genuine deterioration.
Sector shocks. In years with industry-wide stress (2008–2009, 2020), nearly all peers spike together. Relative scoring is less informative when the entire peer group is distressed.
Regulatory language. Banks under formal regulatory agreements (cease-and-desist, memoranda of understanding) are required to use specific disclosure language. This language reads as distressed but may not indicate approaching collapse.
Corpus size. 40 companies is small. The control ceiling is calculated on 30 of them. More companies would produce a more robust baseline. We're adding more.

Who we are

FilingDrift is built and operated by Latent Systems SAS, a French simplified joint-stock company (SAS). We are a small, independent software team — not a hedge fund, not a financial services firm, not a consultancy.

We started with one question: could you have flagged SVB before March 10, 2023 using only public filings? The answer was yes. We built the infrastructure to ask that question systematically across a larger corpus and check whether the answer generalizes.