AFL Glicko Ratings

  Introduction The model I had used for the 2021 AFL season was not satisfactory for the beginning of this season, and hence I made a minor adjustment which significantly improved performance. However, I am still not achieving the results which I desire. Therefore, before the 2023 AFL season in March; I will take a similar process before the 2023 AFL women's competition as well; I will be documenting my progress in my model rework in a long multi-part series of blog posts. Philosophy As the name of the blog suggests, I will continue to use glicko rating (an elo-based system) as the backbone of my model. For the first section of this series, I will be focusing on the team-based model, fully optimising this will allow for a far better player-based model. There are a variety of different parameters which need to be accounted for in the team-based model, and each post in this series will deal with one of them. However, it is important to note that the optimised values for these paramet

  As we approach the end of the home-and-away season, we will certainly see more and more games which shape the composition and permutation of the finals series. In the most recent simulation replicates, fourteen teams qualified for finals (sixteen mathematically), and eleven teams earned a double-chance (twelve mathematically). West Coast and North Melbourne remain the only teams which are mathematically eliminated. Five teams have all but qualified for finals (Geelong, Melbourne, Sydney, Brisbane, and Fremantle), and Geelong have almost guaranteed a double chance. Let's get into this weeks games. RICHMOND vs. FREMANTLE Friday July 22 1950hrs @ Docklands. Richmond playing their "home" game at Damien Hardwick's favourite venue. My model has a very questionable tip considering it's ignorance on players. Dustin Martin and Tom Lynch will miss another round of football, and those outs suggest to me that this match is much closer to a coinflip than the model is suggest

Pretty mixed bag this week, I am expecting some drubbings and a few close ones. PORT ADELAIDE VS. MELBOURNE Thursday April 7 1940hrs* @ Adelaide Oval. And haven't Port Adelaide been disappointing to start the season. It seems Melbourne have been going at 80% all year, and rightly enter the game as strong favourites. Very disappointing considering I was expecting a quality fixture pre-season. Port's forward lines are significantly weakened without Charlie Dixon, and will be unable to kick a big total against the league's best defence. Model Prediction: Melbourne by 17 pts @ 70%. GEELONG VS. BRISBANE Friday April 8 1950hrs @ Kardinia Park. Possibly this week's best game, Geelong's first home game of the season is against quality opposition. After humbling Essendon, Geelong haven't been all too impressive against Sydney and Collingwood, though their comeback against Collingwood was hilarious. Brisbane had the bye last week, and boosted their percentage with an 108

  SIMULATIONS   Ten thousand simulations were run and the following results were obtained. The spreadsheet can be found here .

  SIMULATIONS   Ten thousand simulations were run and the following results were obtained. Here is the link to the spreadsheet: https://docs.google.com/spreadsheets/d/e/2PACX-1vQQ1kAxyJpFHWcWYSPigKC7VM-2jwod1cup8Vklkqj-KXbbLnEIhzsU5-rpwjeVSr6ZY1IaCAenmcXP/pub?gid=1448474542&single=true&output=pdf I have tried making it a .pdf file this time. Let me know if you prefer viewing it on a webpage.

SIMULATIONS   Ten thousand simulations were run and the following results were obtained. Here is the link to the spreadsheet:  https://docs.google.com/spreadsheets/d/e/2PACX-1vQQ1kAxyJpFHWcWYSPigKC7VM-2jwod1cup8Vklkqj-KXbbLnEIhzsU5-rpwjeVSr6ZY1IaCAenmcXP/pubhtml?gid=528182220&single=true There is no time for me to make a Round 2 preview post this week as I have school camp.