Haven't posted an update for a while but given the angst getting player valuations are causing, we've pushed an update to version 0.6.8, allowing users the ability to loop through each team instead to fix issues a little easier as they arise #worldfootballR

jaseziv.github.io/worldfootbal...

Pretty proud to have the {worldfootballR} #rstats library reach 500 starts on Github. Massive thanks to @tonyelhabr.bsky.social and all the other contributors over the journey ❤️

Wild ending in tonight's #NBL25 match between Illawarra and Cairns! Here's how my in-game win probability app saw it - a wild swing. App can be found here nbl-r-shiny.herokuapp.com

After the FIBA break and at the beginning of round 10, here's how my model sees the rest of the #NBL25 season playing out... The model is expecting Melbourne to keep some distance between them and the field www.dontblamethedata.com/models/baske...

Liberating

Inspired by further prompting from Eric, we then expanded this out to look at each playoff round. For the 1st round (wild card games), this method very rarely sees the accuracy go above 50% for any game window. /4

For all playoff games - regardless of playoff round - the peak accuracy comes when using each team's winning percentage with 33 games remaining. /4