PFF Model Predicts Receiver Targets and EPA
PFF uses an XGBoost model and route-level data to predict target locations and introduces metrics: Share of Predicted Targets, Share of Predicted Air Yards, Potential EPA Per Attempt, and EPA Capture Rate. Applied to recent wild-card and divisional games, the measures identified Christian Kirk's WR3 finish, highlighted Drake Maye's high capture rate and Stafford's top potential EPA, and aim to provide more stable analytics for scouting and fantasy decisions.
Key Points
- 1Uses XGBoost and route-level data to predict target locations more reliably than raw target counts
- 2Derives Share of Predicted Targets and Air Yards showing greater stability than actual target metrics
- 3Identifies Drake Maye and Matthew Stafford efficiency differences; helps scouts and fantasy managers prioritize targets
Scoring Rationale
Strong applied-model insights and practical metrics for scouting and fantasy use; limited novelty beyond prior framework introduced last year.
Sources
Public references used for this report.
Practice with real Retail & eCommerce data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Retail & eCommerce problems
