Isolated Death Rate
ISO%CS2v0.1.0 · baseline · validated 2026-07-16What it measures
Share of deaths that were classified as isolated: no teammate close enough to trade, not on an objective, not a last-alive or sacrificial situation.
Formal definition
Deterministic classifier over each death: traded / tradeable-but-missed / isolated / sacrificial / mistimed / unavoidable, using trade window (5s), support distance (700u), objective context, and numbers state. Metric = isolated ÷ total deaths.
Inputs
- kill events
- position samples
- bomb events
- round state
Exclusions
None beyond the standard confidence floor.
Sample & population
- Minimum sample
- 40 deaths
- Baseline population
- Players in the same game/window
- Direction
- lower better
- Unit
- %
Percentile interpretation
Lower is better; persistent high ISO% indicates positioning discipline issues.
Confidence = source confidence × model confidence. Values from baseline models are capped at 0.7. Below-minimum samples display the value grayed out with no percentile.
Example
Lurker dies alone in showers with the nearest teammate 1800u away → isolated.
Known limitations
- Position-sample gaps degrade classification toward 'isolated' — confidence reflects sample density
Current distribution
career window · n=40 eligible playersChange log
- v0.1.0 · 2026-07-16Initial baseline release