The weekly slate published
for everyone. Older weeks stay in this list.
Or upload your own private slate:
Upload your own DraftKings salary
CSV instead. Your upload and any lineups you generate stay in your private browser session and
expire automatically.
Checking for this week's published slate…
Checking for this week's published slate…
2 · Setup
Average Points is the expected
score. Correct for 50/50s and double-ups.
Upload one file per position.
The chosen window supplies both the mean and the sigma.
Which number the optimizer
treats as the player's expected score.
How volatile each position is.
Sigma = mean × CV, and it drives Floor and Ceiling. These are assumptions, not measurements
— replace them once you have game logs.
The DraftKings salary cap for this contest.
Tick any combination. All three is
the DraftKings default; untick to force the FLEX into a narrower set.
IR and OUT are always removed.
Q players are borderline.
Keeps the cheap efficient plays,
so lineups lean on minimum-salary punts. It removes only players who are provably useless
— someone cheaper AND higher scoring — so it cannot change your single best lineup.
Removes anyone at or below this
price. A rough proxy for "is he actually starting". Locked players ignore floors.
Talent overlay. We look at
each player's Madden ratings and whether he has an X-Factor, then apply our proprietary adjustment
to his projection. It can raise or lower a player. Included for experimentation; volatility
continues to follow the selected sigma model.
Home field boost
Drops anyone projected below
this. Unlike a salary floor it targets low producers directly, whatever they cost. 0 = off.
Output
How many lineups to generate.
Maximum 100 per set.
How different the lineups are
from each other. Your best lineup usually stays similar; higher diversity can lower the weakest
lineups in exchange for more variety.
Overlap is the most players two
lineups may share. Set 9 to turn it off.
Overlap is the most players
two lineups may share. Exposure is the ceiling on how often one player appears. Set
overlap 9 and exposure 100 to turn both off. If the full count cannot be found, the largest
set is shown with an exact warning, and DraftKings export stays disabled until the set is
complete and compliant. Maximum 100 lineups.
Players that must appear in every
lineup. Set them in the Player pool tab.
none
Players that must never appear.
Set them in the Player pool tab.
none
Simulation
Portfolio is normally the right choice. Full Pool may
contain tens of thousands of candidates and is intentionally much slower.
EXPERIMENTAL. p controls the whole shape: p→1 is
spikier with more zeros, p→2 becomes gamma. Its zero mass is also
constant within a position until real usage data replaces the CV.
Uses whatever games a player actually has. Under 2 games
falls back to position and says so. No blending.
Measures the lineups you already
have across many simulated Sundays.
Samples one lucky Sunday.
Deliberately random — re-roll for a different draw. Not a projection, and that is the point.
Run the optimizer first.
Diagnostics
Inspection tools. None of these pick lineups for you.
A single draw with per-player scores. At N=1 the ranking
is pure noise — do NOT select lineups from it. It exists so you can
see what one Sunday looks like and confirm the distributions are sane.
Same lineups, same sigma, same seed — only the shape
changes.
Re-solves one lineup with PARETO and the exact ILP solver
under the same player-pool and FLEX rules. ILP is a diagnostic proof,
not a weekly portfolio generator.
Import a file, set it up, hit run.
Salary sweeper
Reruns the whole model at every cap and pools the results.
The best lineup at $49,600 uses different players than at $50,000, so the
sweep reaches rosters a single cap never can.
Maximum 100 lineups at each salary cap.
Tuning
Always runs BOTH pruning and Top N — comparing them
is the point, so there is no mode selector here.
FLEX can hold an RB, a WR or a TE. This tries every
combination of which are allowed — RB+WR+TE, RB+WR, RB+TE, WR+TE, RB
only, WR only, TE only — so you can see what each restriction costs
before choosing one. It multiplies the work by 7.
The other positions hold at their Optimizer values. Pruning
is solved ONCE as the baseline — it does not depend on the counts.
On, each pool AND the merged union pass through portfolio
selection, so results respect your limits and are safe to export.