Placement Probability Added
PPAFNv0.1.0 · baseline · validated 2026-07-16What it measures
How much better a player placed than the survival baseline expected, phase by phase. Rewards outliving the lobby's hazard curve, not just one lucky endgame.
Formal definition
At each storm phase, expected placement percentile = players remaining ÷ lobby size. PPA = actual final placement percentile − mean expected percentile across phases survived. Heuristic baseline (documented), not a fitted model.
Inputs
- storm phase events
- players-remaining counts
- final placement
Exclusions
None beyond the standard confidence floor.
Sample & population
- Minimum sample
- 12 matches
- Baseline population
- Players in the same event/window
- Direction
- higher better
- Unit
- percentile pts
Percentile interpretation
High PPA with low eliminations = survival specialist; see Engagement Selection.
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
Surviving to top 10 from a contested drop where 40% of the lobby died early yields high PPA.
Known limitations
- Baseline is uniform-hazard; zone RNG and drop contest are not conditioned in v0
- Requires replay/recording-derived phase data or official per-match placements
Current distribution
career window · n=30 eligible playersChange log
- v0.1.0 · 2026-07-16Initial baseline release