Brickroad
Brickroad
IndexSignalsBlog
/Index//

Product

  • Information Frontier Agent
  • Vendor Management Agent
  • Product Tour
  • Pricing

Solutions

  • All Solutions
  • Atlas
  • Wayfinder
  • Horizon

Suppliers

  • Sell Your Data
  • Start Onboarding
  • Programmatic Data License

Community

  • Public Index
  • Signals
  • Blog

Company

  • About
  • Team
  • Careers
  • Brand

Connect

  • LinkedIn
  • X
PrivacyTermsCookies

© 2026 Brickroad

/Index/Sov.ai/Sov.ai
S

Sov.ai

SOV.AIManage supplier listing

Model-derived clinical-trial outcome dataset delivered as two joined endpoints. clinical/trials carries roughly 75 metadata fields per trial (sponsor, condition, intervention type and name, trial status, key dates); clinical/predict attaches to those trials a predicted probability of success, an expected duration, a modelled economic impact including potential market reaction, a composite success score and a sponsor class. Built from regulatory filings and biochemical data using deep-learning encoders and language models, refreshed weekly on Fridays as filings become available, indexed by ticker and date with full history callable in one request. The vendor reports 87% ROC-AUC and claims the highest among commercially available solutions.

Open buyer room →
Sov.ai/Sov.ai
SampleCoverage

Sample

Brickroad customers

Sample this dataset before you buy it.

Your sourcing agent asks Sov.ai and files the sample in your catalog — private to you.

Start 7-day trial→Nothing is charged until the trial ends.

Coverage

Universe, instruments and categories.

Industry
Financial Exchanges & DataHealth Care Technology
Instruments
equitiesoptions
Categories
AlternativeFundamentalSentiment
Regions
US
Sample tickers
MRNABNTXREGNVRTXBIIBALNYSRPTIONSARGXCRSP
Dataset card
Type
not stated
Format
Tabular panels (ticker/date indexed) delivered through a native Python library with a full_history flag for bulk pulls and per-ticker subsetting, documented as a realtime dataset catalogue; public Jupyter/Colab tutorials ship as working examples. Weekly append cadence rather than streaming.
Volume
Coverage of 850-plus tickers with history from 1 November 1999, i.e. roughly 27 years, at an intake the vendor puts at ~1,052 newly launched clinical trials per week. That cadence alone implies order 50,000 new trials per year and, over the full window, a trial panel plausibly in the hundreds of thousands of records, each carrying roughly 75 descriptive fields plus five or more model outputs, joined to a ticker/date key.
Users
N/A — subscription data/API product for institutional and quant research with no published account or seat count; corporate records show a one-person research operation, so the licensed-client base is plausibly in the tens rather than hundreds.
History
27 years
Update frequency
not stated
Growth
Active — the dataset is described as refreshed weekly on Fridays as filings become available, is documented as part of a broader realtime dataset catalogue, and ships runnable public notebooks for the current pipeline.
Launched
~2018-2021 — the corporate record carries a registration identifier created in 2018, and the vendor's public research repository and dataset documentation appeared in the period that followed; the clinical-trials dataset itself has no separate dated launch announcement.
Delivery
not stated
Entity mapping
not stated
Sample
not stated
Point-in-time
not stated
Licence
not stated

supplier index read from their site

Sov.ai has not added their own details yet. Not yet on file:

  • Dataset
  • Data dictionary
  • Coverage
  • Provenance
  • Rights & data handling