Observed arrival · 2026-10-14
SymML: machine learning you can read
Formetis presents SymML, a machine-learning system that aims to return short algebraic formulas instead of opaque prediction models.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Teams needing interpretable models for tabular data
- Worth noticing
- Its credit-risk illustration adds a fixed three points per missed payment; the page says its displayed formulas are examples, not actual outputs.
Field notes
The page frames the product around formulas that can be inspected rather than hidden model parameters. Its sample equations span debt and missed payments, atomic spacing, equipment temperature, and gene interactions; Formetis explicitly distinguishes these clarity-focused illustrations from formulas learned on a user's data. The company says the method was developed at KIT and can search billions of candidate formulas on standard cloud GPUs.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue