FPL_Mou

[FPL_Mou @FPL_Mou]

Final 2026 NBA draft model top-30

[FPL_Mou @FPL_Mou]

Final 2026 NBA draft model top-30

[FPL_Mou @FPL_Mou]

@Starro____ Thanks mate!

[FPL_Mou @FPL_Mou]

Final 2026 NBA draft model top-30

[FPL_Mou @FPL_Mou]

@thegrantedwards the results in the dashboard and google sheets link should be consistent now,
made an update to the model for better year to year comparisons

[FPL_Mou @FPL_Mou]

Brief explanation of the model - https://t.co/QLtOkQir9i

[FPL_Mou @FPL_Mou]

Results are now an ensemble of the player similarity based model and ML models to estimate tier probabilities. This improves PR-AUC across higher tiers to 0.37

[FPL_Mou @FPL_Mou]

@himganj153 Substack link in the main tweet usually gets suppressed imo

[Himanish Ganjoo @himganj153]

The question of the pace of a pitch has bugged me for a long time. I wrote down an exploration of the pace of pitches, comparing different countries and discovering three kinds of surfaces. And yes, "fast" pitches really mean "bouncy".

Read more: https://t.co/IQpOKOetBb

[Cruel Angel PHD🇵🇷 @AmericanNumbers]

World Cup 2026 Model v1 (Notes follow):
https://t.co/hUlih7XTCZ

[FPL_Mou @FPL_Mou]

@DannyDimes1000 But the output would also have a projected target variable along with the rank, no?

[FPL_Mou @FPL_Mou]

@mikegrib8 @DannyDimes1000 Have limited my reference sample to 15 seasons as well (assumption, not quantitatively derived obviously)

[FPL_Mou @FPL_Mou]

@DannyDimes1000 Ignored consensus as a variable for similar reasons but accuracy does suffer.

[FPL_Mou @FPL_Mou]

@mikegrib8 Chart Y

[FPL_Mou @FPL_Mou]

@thegrantedwards Still tweaking the hyperparameter weights to fine tune it.
I'll post a final (hopefully) version soon

[FPL_Mou @FPL_Mou]

Used ML based models to estimate a players probability of making the nba and then derived the other outcome probabilities using the similarity based approach.

Updated top-60 for the 2026 draft

https://t.co/gnKZlZNiqI

[FPL_Mou @FPL_Mou]

Converted the draft model results and validation metrics in Google sheets to tables using plotly.
A cleaner visualization than before.

[FPL_Mou @FPL_Mou]

Used ML based models to estimate a players probability of making the nba and then derived the other outcome probabilities using the similarity based approach.

Updated top-60 for the 2026 draft

https://t.co/gnKZlZNiqI

[FPL_Mou @FPL_Mou]

@AtTheLevel Peat

[FPL_Mou @FPL_Mou]

1. RMSE has dropped from ~0.7 to 0.55 post update
2. Correlation, spearmans rho and kendalls tau all see slight improvements from before

[FPL_Mou @FPL_Mou]

@DannyDimes1000 From here
https://t.co/TPnSS4HkuB

[Kostya Medvedovsky @kmedved]

Two new additions to the DARKO spreadsheet (https://t.co/mVkemwg9tS):

1) A pace RAPM estimate, which tells you how much impact each player is projected to have on a team's average length of possession, broken out by offense vs. defense.