GWS’ reign at the top of both MoS Team Rating Systems was very short-lived, and they now find themselves sitting behind Collingwood on MoSSBODS, and behind Collingwood and Geelong on MoSHBODS.

I think it’s in the nature of we humans to focus more on what we’ve narrowly missed than on what we’ve narrowly won, so I’ll try to avoid that bias here and reflect more on the fact that our debutant forecaster, MoSHPlay, is ahead of the bookies on head-to-head tips, probability forecasting, and - at least compared to Bookie_Hcap - on margin prediction.

Anyone who ever tells you they have a 100% error-free program or script that does anything much more than print out “hello world” is certifiably deluded.

Turns out that the MoS twins still aren’t buying the “higher scores are coming” narrative.

Quick update now that the teams have been announced for Thursday night’s game.

The TAB has framed Total markets only for Thursday’s and Friday’s games so far, so there’s not a great deal to talk about.

With the benefit of a few days’ reflection, I think I’d rate my satisfaction with MoS models’ performances in Round 1 at maybe a six or seven out of 10. It was, clearly, a difficult round to predict, but I’d have preferred MoSHPlay to have fared a little better than it did, even after adjusting for the Sparrow/Lewis misadventure.

For only the third time in their history, and for the first time in 12 months, GWS sit atop both MoS Team Rating System rankings after jumping three places on MoSSBODS and four on MoSHBODS to nudge Richmond back into second on both Systems.

So, what to make of all that then?.

It’s clear already that MoSHPlay is going to add some welcome variability to the MoS forecasters this year.

MoSSBODS and MoSHBODS are always living in the past, since they take their cues from history and are blind to things like rule changes that might influence the patterns of scoring in the new season.

With the teams just announced for tomorrow night’s game, MoSHPlay has made its first ever pre-game forecasts, tipping the Tigers to win by 44 points, and assigning them about an 89% probability of victory.

It’s incredible just how rusty you become in running your code and cranking out tables after only six months away from the discipline …

With the benefit of four months’ or so reflection, it’s a bit easier to make a more rational assessment of the performances of the MoS menagerie of models in 2018.

Like their respective supporters, West Coast rose and Collingwood fell at the end of the Grand Final on both Systems on Saturday, the Eagles finishing 3rd on both, and the Pies taking 4th on MoSSBODS and 5th on MoSHBODS.

Well that was the quite the Grand Final, wasn’t it?

There’s again very little debate amongst our four score forecasters this week, with all of them predicting totals in the 158 to 162.5 range, and victory margins for Collingwood in the 6 to 12 point range.

The 2018 AFL Grand Final pits the team that finished 2nd in the home-and-away season against the team that finished 3rd for the fourth time since 2000. .

Ratings superiority counted for little this week, as the number 1 and 2 rated teams on both MoS Systems came away with Preliminary Final losses.

It was another good week for most forecasters of all forms, with all but two of the Head-to-Head Tipsters selecting both winning teams, the average mean absolute error (MAE) for the Margin Predictors coming in at 11.3 points per game, and large, positive probability scores for all of the Head-to-Head Probability Predictors.