Goodguy AI Labs · Open weekly experiment

The Fantasy Fruit Fly

Can a fruit-fly decision circuit help call fantasy football? We pair it with a statistical companion and give both public NFL facts. A selector trained on held-out weeks sets their contribution by stat; for some stats, the companion supplies the whole forecast. Together they build the football stat lines behind the rankings.

Software keeps records straight: stable identities, dates, roles, and source receipts. Neither model receives analyst rankings, outside picks, or a fantasy answer key.

Follow the Fly through the season: weekly calls, game-by-game grades, and what it learns next.

Board: Checking release…
Scoring: PPR · Half PPR · D/ST
Answer key: None

See the Fly’s rankings Open the lab notebook

Meet the decision-maker.A new mark for a very serious little experiment.

Checking for this week’s release…

Rankings stay blank until a complete release passes the page’s checks.

The Fly’s player rankings

Week 1 rankings by position.

The Fly-derived circuit and its statistical companion make the forecasts together, using the public NFL record to project attempts, yards, touchdowns, carries, targets, receptions, and defensive events. A selector trained on held-out weeks sets their contribution for each stat—and gives the companion the full contribution for some. Then the scoring bank turns the combined stat lines into PPR, Half PPR, or D/ST points. Open a row to see the range and role reference.

Week 3 / kickoff batches

Full-week rankings, updated before kickoff.

Checking this batch…

ThursdayFull-week board; ATL–GB kicks off first
Sunday morningRefresh games that have not kicked off
Monday morningRefresh Monday’s game before kickoff

Each game’s forecasts stay frozen after kickoff.

What changed before this board?

First, fix the inputs. Think of the Fly as a marble machine and NFL facts as the marbles. Some workload numbers mixed a player’s games with a different set of team games. We matched them up: 10 carries out of 20 team carries means half the work. Trades and missed games now use that same rule. We also fixed how the simulation shares catches and touchdowns among players.

Then, take the lessons in order. The Fly starts with history through 2025, then learns from completed NFL games one week at a time. A finished game can inform the next week’s calls, never its own saved prediction. Sunday and Monday refresh the facts for upcoming games as roster, injury, and weather reports arrive; they do not learn again from the same results.

Finally, make the football call. A statistical companion and the Fly-derived circuit learn from the NFL record. Tests on held-out historical weeks determine how much each contributes. Together they produce football stat lines; PPR and Half PPR rules do the arithmetic afterward. Fixing the machinery gives us a better experiment. The next games tell us whether it makes better picks.

Week 5 / weekly updates

New facts. Another lesson. A full board.

Use Games for an individual matchup, or browse every position and FLEX for the whole week.

What went into this week’s calls?

Check last week’s answers. We kept the Week 4 board people saw and checked it against the NFL results. Carries, targets, yards, touchdowns, turnovers, and defensive events give the Fly its next lesson. The Week 4 report card shows the misses by position and the learning record behind them.

Learn, then refresh the facts. The system trains its statistical companion and Fly-derived circuit on the completed games, then checks their work on held-out history. Each run refreshes rosters, injury and availability reports, recent workload, and weather context before making Week 5 calls. A report that has not arrived stays unknown; it does not become a clean bill of health. The same completed week is not rewarded twice.

Keep the whole week in view. These are full-week rankings. Thursday, Sunday and Monday runs refresh games still ahead as new reports arrive. Each game’s predictions lock at kickoff. The Fly and its companion project the football stats first; the scoring rules turn those calls into PPR, Half PPR, and D/ST points. Expert rankings remain a comparison, not a lesson.

Week 6 / Saturday update

Fresh inputs. A full board.

Browse every position and FLEX, or use Games to isolate a matchup.

What changed, in plain English?

A clearer football record. We corrected how the system counts attempts, targets, snaps, and team workload, and how it handles missing information. Then we rebuilt the model on the corrected data and taught it Weeks 1–5 in order. This is a new learning state; the original weekly predictions stay saved and are graded as published. Analyst rankings are for comparison, not training.

New reports for games ahead. Saturday’s update uses current rosters and injury and availability reports. The Fly receives temperature and wind forecasts for nine of the 13 remaining games; three stadiums have uncertain exposure, and one game is indoors.

One board, game by game. Thursday’s matchup was reconstructed after kickoff from the pregame snapshot; Thursday game stats were not used. The other games can be refreshed before kickoff while earlier calls stay frozen.

Find an entity

PositionScoring

Loading the released board…

Weekly football rankings
Rank	Player	Matchup	Projected points	Likely range	Actual	Points off	Actual rank	Role reference
The board appears after JavaScript verifies the release contract. The Fly gets the public record; it does not get somebody else’s answer.

The released board scrolls inside this frame. Search or filter first, then scroll to inspect more players.

Week results

How close were the Fly’s calls? These grades use the saved rankings, the NFL results, and the scoring format you’ve selected.

Status: Results appear after the weekly record is verified.

One weekly receipt

Wednesday report card

Decision groups · points and range

How did the Fly do on the players it put near the top? We check its top 12 QBs, 24 RBs, 36 WRs, 12 TEs, and all 32 defenses separately from the full pool. Raw NFL outcomes are the Fly’s lessons; analyst rankings are comparisons only.

Position	Graded	Average points off	Scores in range

Download component error matrix ↓Download coverage record ↓

Same-player comparison

FLEX · Half PPR

Only players ranked by all three are compared.

Original public board, corrected replay, and FantasyPros ECR are checked against the same players and actual results. Lower rank error is better; higher percentages are better.

Ranker	Point error	Rank error	Pairwise order	Top-range hits

Point error is average fantasy points off; ECR publishes ranks only. Rank error is average places off. Pairwise order is the share of player pairs ordered correctly. Top-range hits shows precision / recall: how many selected players finished inside the scoring cutoff / how many top finishers were selected.

Coverage and starter range

Whole-board comparison · fewer places off is better
Ranker	Imported rankings	Fly entries compared	Fly: places off	Ranker: places off
External comparisons appear after the weekly data is verified.

Position-by-position comparisons

Ranker	Position	Fly entries compared	Fly: places off	Ranker: places off

No rank in archived feeds

Captured expert feeds can rank FLEX pools, while dedicated position feeds have their own scope. A player without a rank in the archived feed was not assigned a last-place rank.

The experts’ complete ranking lists

We also check each expert’s entire imported list against NFL results, including players the Fly never ranked. “Graded / imported” shows the coverage; an unresolved NFL identity is not silently scored as zero. This is a separate report: the Fly has no saved forecast for those extra players, so they cannot enter a head-to-head score. A longer list also changes the size of the ranking pool.

Ranker	Position	Graded / imported	Ranker: places off

How do we grade the Fly?

Think of a teacher checking a worksheet. The Fly has already written its answers. The games give us something to check them against.

Keep the original calls.

We grade the exact board people saw, not a new set of predictions. Each call stays attached to its player, team, game, and week.

Check what happened on the field.

We match the recorded NFL stats to stable player IDs, then apply the same scoring rules used for the forecast. PPR awards one point per reception; Half PPR awards half a point. D/ST uses the defensive rules listed in the lab notes.

Count the misses.

The points-off column is projected minus actual. A call of 20 points against a score of 15 is +5: five points high. A call of 10 against 15 is −5: five points low. Those two calls have an average miss of five points, even though their high/low lean balances to zero.

Compare the whole board.

Every Fly entry is checked against the full imported expert rankings. The expert table measures rank order, not projected points. For entries with both forecasts, the Fly, each ranker, and the actual results are reordered within the same matched player pool and position. The whole-board average pools those misses across all positions; you can also inspect each position. PPR is compared with PPR; Half PPR with Half PPR. Ties share an average rank. Fourth versus tenth is a six-place miss. An absent rank stays absent, not a made-up last-place pick.

Give the Fly its next lesson.

The Fly learns from raw NFL stats: workload, yards, touchdowns, turnovers, and defensive events. Expert rankings are only a comparison on this page. They do not become the Fly’s homework answers. The weekly report records the results; learning receipts track what the system has used.

Average points off: The size of the miss, averaged across the graded entries. Researchers call this mean absolute error, or MAE. Mean means average; absolute means a miss counts in either direction. Lower is better for point accuracy.
High / low lean: The average signed miss, also called bias. A positive value means the Fly ran high overall; a negative value means it ran low. A value near zero can still hide large misses in opposite directions.
Scores in range: How often the actual score landed inside that entry’s likely range. The range runs from the 10th to the 90th percentile: the middle 80% of simulated scores. Coverage of 65% means about 65 of every 100 graded scores landed in their own predicted ranges.
Places off: The average distance between a predicted rank and the actual rank, measured in ranking places. It tells us whether the order was useful. A good order and a close point projection are two different tests.
Professional analysts & ECR: FantasyPros ECR is its Expert Consensus Rankings. Individual rankers appear as numbered professional analysts; the numbers are labels, not a leaderboard. Each row uses its own shared player pool, so compare the Fly and ranker within that row.
Provisional results: The games are graded, but official stat corrections can still change the result. A correction gets a new dated results record; it does not rewrite the Fly’s saved predictions or give the same week a second cumulative reward.

Human vs. model

Are you smarter than a fruit fly?

Choose one player from each same-position pair before the first listed kickoff. Pairs come only from the current release. This browser-only practice round has no verified leaderboard and is not personal roster advice.

Waiting for a current board before setting a lock time.

Five pairs will appear only when the current released rankings contain enough same-position comparisons.

Practice score

Make a call first. Final outcome records are needed before this round can be scored.

Honor system: we do not send or verify your picks. If browser storage is unavailable, the page will say so rather than pretending your calls were saved.

ELI5: the method

Put both forecasts to the test.

Here is the marble-machine version. Software puts clean NFL facts in the hopper and keeps every player and team attached to the right record. A statistical companion and the Fly-derived circuit make forecasts; a selector trained on held-out weeks chooses their mix for each stat, sometimes giving the companion the full contribution. The scoring bank turns the resulting football stat lines into fantasy points.

01
We load the obvious stuff.
Schedules, stable IDs, prior workload, team and opponent context, scoring rules, and a cutoff-safe depth-chart role reference enter the chute. It is the public NFL record—the stuff any fantasy player can find with a little digging. We do not hand either model a ranking.
02
The two models get to work.
The statistical companion and measured BANC path learn from the same untouched history. Bzzz. Neither route receives somebody else’s fantasy answer.
03
Held-out weeks choose the mix.
Historical tests set each model’s contribution stat by stat. For some stats, the selector gives the companion the full contribution. No one dials up a favorite.
04
Together, they build the stat line.
The forecasts combine to project volume, yards, touchdowns, turnovers, sacks, and points allowed. The scorekeeper translates those stats into PPR, Half PPR, or D/ST points.
05
A pretty normal player pool.
One QB, two RBs, three WRs, and two TEs per team, plus every D/ST. The depth chart keeps the right people in the room; the selector combines their forecasts for each stat.
06
How much of the call is Fly?

The Fly-derived network works alongside a statistical companion trained on the same NFL history. Performance on unseen games determines their mix for each stat. For some stats, the companion gets the full contribution. That gives us something to track each week: where the Fly helps, and where it doesn’t.

Data notes

Bzzz. Inside the Fantasy Frankenfly.

A quick lab note on the records, wiring, and rules behind this week’s calls. The page reads one release file and shows its work instead of filling the board with stand-in rankings.

Release information

Status: Checking for a release…

Primary sources & attribution

Sources appear after the current release passes its contract.

This release’s files

Sources will appear with a released dataset.

Limitations

Limitations will appear with a released dataset.

The Fantasy Fruit Fly

Week 1 rankings by position.

Wednesday report card

FLEX · Half PPR

Keep the original calls.

Check what happened on the field.

Count the misses.

Compare the whole board.

Give the Fly its next lesson.

Unrated players

Are you smarter than a fruit fly?

Put both forecasts to the test.

We load the obvious stuff.

The two models get to work.

Held-out weeks choose the mix.

Together, they build the stat line.

A pretty normal player pool.

How much of the call is Fly?

Bzzz. Inside the Fantasy Frankenfly.

How this release was checked