AVAIL 0
MY PICKS 0
OPPONENT 0
ROUND 1
QB 0
RB 0
WR 0
TE 0
K 0
DEF 0
My Roster
Projected Total
0.0

No Data

Click INITIALIZE to fetch NFL stats
and train prediction models.

Target Intel

Load data to get recommendations.

Positional Scarcity
Load data to see scarcity.
Bye Week Conflicts
Draft players to check conflicts.
Sleepers & Busts
Load data to see model vs ADP gaps.
Handcuff Alerts
Draft RBs to see handcuff options.
Opponent Drafts
None yet.

OverADP — How to Use the War Room

OverADP is an AI-powered fantasy football draft assistant. It uses machine learning trained on 7 years of NFL data to project player performance and guide your draft picks in real-time.

Understanding the UI

Player Pool (Left Panel)

Each player row has two action buttons:

ColumnMeaning
VBDValue Above Replacement — how many more points this player scores vs a replacement-level player at the same position. Higher = more valuable.
PROJProjected fantasy points for the season (half-PPR by default).
CI80% Confidence Interval [low–high]. Wider = more uncertain. Rookies have much wider CIs.
RISKlow / medium / high — based on prediction uncertainty. High risk = boom-or-bust.
BYEBye week for this player's team. Watch for conflicts with your other starters.
ADPAverage Draft Position from Fantasy Football Calculator — where the market values this player.

Draft Board Sort

Players are interleaved by position (RB → WR → QB → TE) within each VBD tier, so you don't see 50 RBs in a row. This mimics how a real draft flows.

My Team (Center Panel)

Players are auto-assigned to roster slots based on position:

Bye weeks are shown next to each player. Red = bye conflict with another starter.

Right Sidebar Panels

PanelWhat It Shows
Pick AdviceTop 5 recommendations based on VBD + roster need bonuses. "MUST DRAFT" = starter slot still open late.
Positional ScarcityDrop-off from elite to replacement level per position. Higher dropoff = position is scarce = draft early.
Bye ConflictsWarns when multiple starters share a bye week. Critical = no bench coverage. Warning = bench available.
Sleepers & BustsCompares model rank vs ADP. Sleepers = model ranks higher than market. Busts = market overvalues.
Handcuff AlertsBackup RBs on the same team as your starting RBs. If your starter goes down, the handcuff takes over.
Opponent DraftsTracks what positions opponents are taking — watch for position runs.

Key Concepts

VBD (Value Based Drafting)

VBD = Projected Points − Replacement Level Points. The replacement level is the projected points of the last player typically drafted at each position (including bench). This means even bench-worthy players get positive VBD, helping you compare value across all rounds — not just the early ones.

Positional Scarcity

Measures the drop-off from the elite tier to replacement level at each position. If QB has a small dropoff but TE has a huge one, you should prioritize TE — because the quality falls off a cliff after the top TEs are gone.

How it's calculated: For each position, OverADP finds the projected points of the #1 player (elite) and the projected points of the last starter that would be rostered across all teams (replacement). The difference is the scarcity score.

Scarcity LevelWhat It MeansDraft Strategy
High ScarcityHuge gap between elite and replacementDraft this position early — waiting means getting a much worse player
Medium ScarcityModerate dropoffBalanced — draft when value aligns with your pick
Low ScarcityShallow dropoff — many comparable optionsSafe to wait — replacement-level players are almost as good as "starters"

Example: In a 12-team league starting 1 TE, the #1 TE (Kittle, 136 pts) and the #12 TE (~97 pts) differ by 39 pts. But the #1 QB (Lamar, 245 pts) and #12 QB (~170 pts) differ by 75 pts. However, QB scarcity is often lower because there are only 12-14 starting QBs rostered, while TE has a steeper talent cliff at the top. The scarcity panel shows you which positions have the steepest cliffs so you can draft accordingly.

Confidence Intervals

The 80% CI shows the range where the model expects the player's actual points to land. Narrow CI = reliable projection. Wide CI = uncertain. Rookies, injured players, and players with changing situations have wider CIs.

Model vs ADP

Our CatBoost model has a 0.752 average correlation with actual fantasy points, beating ADP's 0.678. The model's edge is largest at TE (+38% MAE improvement) and WR (+25%). When the model and ADP disagree strongly, it flags sleepers (model > ADP) and busts (ADP > model).

Handcuff Alerts

A handcuff is a backup RB on the same NFL team as your starting RB. If your starter gets injured, their backup typically takes over the starting role and inherits most of the carries — making them extremely valuable as insurance.

Why it matters: If you drafted Saquon Barkley in the 1st round and he goes down in Week 3, his backup (who you can draft in the last round for almost nothing) suddenly becomes a top-15 RB. Without the handcuff, you're scrambling on waivers.

Handcuff TypeDescriptionPriority
Must HandcuffYour RB1's backup — protect your 1st/2nd round investmentHigh — draft in late rounds
ConsiderYour RB2/RB3's backup — nice insurance but less criticalMedium — if bench space allows
AvailableOther backup RBs still on the boardLow — only if you have empty bench slots

Strategy: Draft your stud RB's handcuff with one of your last picks. It's like buying insurance — you hope you never need it, but if you do, it saves your season. The Handcuff Alerts panel shows you which backups are still available for RBs already on your roster.

Ensemble Model

OverADP uses a 4-model ensemble — Ridge Regression, Random Forest, XGBoost, and CatBoost. Each model makes predictions independently, and the final projection is the average of all four. This reduces overfitting and produces more reliable projections than any single model alone.

ModelStrengthBest For
RidgeLinear relationships, stable with small dataBaseline — prevents wild predictions
Random ForestNon-linear patterns, resistant to outliersCapturing interactions without overfitting
XGBoostGradient boosting, strong on tabular dataRB/TE projections
CatBoostOrdered boosting, best generalizationQB/WR/TE — wins validation on most positions

Feature selection: We ran an ablation study and found that derived features (teammate dependency, playmaker metrics like RACR/WOPR) were harmful — they're collinear with base lag features and added noise. The model performs best with clean lag features + ADP + age curves + regression-to-mean adjustments.

Data Sources

Accuracy

PositionR² (CatBoost)R² (ADP-only)MAE vs ADP
QB0.4400.224+24% better
RB0.5850.448+3% better
WR0.6040.408+25% better
TE0.5880.250+38% better

Walk-forward validated 2022-2025 (train on past, test on future). CatBoost wins all 4 positions. All features are lagged to prevent data leakage. R² measures out-of-sample accuracy — how well the model predicts players it's never seen before.

Model vs ADP — Head to Head

We tested our model against ADP (Average Draft Position) using walk-forward validation on 2022-2025. ADP represents the "wisdom of the crowd" — where thousands of fantasy players are drafting. Our model beats it at every position:

MetricOverADPADPWinner
Avg R²0.5540.333OverADP
Avg Correlation0.7520.678OverADP
Best edgeTE +38% MAEOverADP

What this means: Our model explains 55% of variance in fantasy points vs ADP's 33%. The biggest edge is at TE (38% less error) and WR (25% less error). ADP is already decent at RB, so the model's edge there is smaller (3%).

PositionModel R²ADP R²MAE Improvement
QB0.4400.224+24%
RB0.5850.448+3%
WR0.6040.408+25%
TE0.5880.250+38%

Why we beat ADP: ADP is a popularity contest — it reflects name recognition and recency bias. Our model uses statistical regression, age curves, and ensemble machine learning to find players the market misvalues. The biggest edge is at QB — ADP consistently undervalues dual-threat QBs (Lamar Jackson, Josh Allen) because their rushing value isn't obvious from traditional stats.