Click INITIALIZE to fetch NFL stats
and train prediction models.
Load data to get recommendations.
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.
Each player row has two action buttons:
| Column | Meaning |
|---|---|
| VBD | Value Above Replacement — how many more points this player scores vs a replacement-level player at the same position. Higher = more valuable. |
| PROJ | Projected fantasy points for the season (half-PPR by default). |
| CI | 80% Confidence Interval [low–high]. Wider = more uncertain. Rookies have much wider CIs. |
| RISK | low / medium / high — based on prediction uncertainty. High risk = boom-or-bust. |
| BYE | Bye week for this player's team. Watch for conflicts with your other starters. |
| ADP | Average Draft Position from Fantasy Football Calculator — where the market values this player. |
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.
Players are auto-assigned to roster slots based on position:
Bye weeks are shown next to each player. Red = bye conflict with another starter.
| Panel | What It Shows |
|---|---|
| Pick Advice | Top 5 recommendations based on VBD + roster need bonuses. "MUST DRAFT" = starter slot still open late. |
| Positional Scarcity | Drop-off from elite to replacement level per position. Higher dropoff = position is scarce = draft early. |
| Bye Conflicts | Warns when multiple starters share a bye week. Critical = no bench coverage. Warning = bench available. |
| Sleepers & Busts | Compares model rank vs ADP. Sleepers = model ranks higher than market. Busts = market overvalues. |
| Handcuff Alerts | Backup RBs on the same team as your starting RBs. If your starter goes down, the handcuff takes over. |
| Opponent Drafts | Tracks what positions opponents are taking — watch for position runs. |
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.
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 Level | What It Means | Draft Strategy |
|---|---|---|
| High Scarcity | Huge gap between elite and replacement | Draft this position early — waiting means getting a much worse player |
| Medium Scarcity | Moderate dropoff | Balanced — draft when value aligns with your pick |
| Low Scarcity | Shallow dropoff — many comparable options | Safe 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.
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.
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).
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 Type | Description | Priority |
|---|---|---|
| Must Handcuff | Your RB1's backup — protect your 1st/2nd round investment | High — draft in late rounds |
| Consider | Your RB2/RB3's backup — nice insurance but less critical | Medium — if bench space allows |
| Available | Other backup RBs still on the board | Low — 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.
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.
| Model | Strength | Best For |
|---|---|---|
| Ridge | Linear relationships, stable with small data | Baseline — prevents wild predictions |
| Random Forest | Non-linear patterns, resistant to outliers | Capturing interactions without overfitting |
| XGBoost | Gradient boosting, strong on tabular data | RB/TE projections |
| CatBoost | Ordered boosting, best generalization | QB/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.
| Position | R² (CatBoost) | R² (ADP-only) | MAE vs ADP |
|---|---|---|---|
| QB | 0.440 | 0.224 | +24% better |
| RB | 0.585 | 0.448 | +3% better |
| WR | 0.604 | 0.408 | +25% better |
| TE | 0.588 | 0.250 | +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.
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:
| Metric | OverADP | ADP | Winner |
|---|---|---|---|
| Avg R² | 0.554 | 0.333 | OverADP |
| Avg Correlation | 0.752 | 0.678 | OverADP |
| Best edge | TE +38% MAE | — | OverADP |
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%).
| Position | Model R² | ADP R² | MAE Improvement |
|---|---|---|---|
| QB | 0.440 | 0.224 | +24% |
| RB | 0.585 | 0.448 | +3% |
| WR | 0.604 | 0.408 | +25% |
| TE | 0.588 | 0.250 | +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.
You're spending $100+ on your league — don't waste it drafting blind.