AFLW Round 4 Results - Almost Halfway

/

After 4 weeks, WoSHBODS is at 78% accuracy and has an 18.0 Margin MAE and a 21.8 Totals MAE. There isn’t much around to compare those number to, but they seem quite acceptable to me.

We can review WoSHBODS’ Accuracy and MAE by subdividing games based on the final margin, which we do in the table at right.

It shows that WoSHBODS is now 24 from 26 in games that have been won by 2 goals or more, but also that its MAE is under 13 points per game across all the games won by under 4 goals.

In games won by less than 2 goals, WoSHBODS is only 4 from 10 in terms of accuracy, which is just slightly worse than chance.

We can also look at how WoSHBODS has performed on a team-by-team basis, firstly in terms of MAE, which we do in the table at left.

It shows that the final margins in games involving Hawthorn, Essendon, or Fremantle have been very well forecast - generally within two goals of the actual margin - while those in games involving Western Bulldogs, Gold Coast, or West Coast have been less well forecast and in error by as much as 4 or 5 goals.

Realistically, I think, any statistical modeller who chooses to produce AFLW forecasts is going to struggle with some teams more than others for at least a few more more years yet.



We can also review how well WoSHBODS has estimated the victory probabilities of each team by looking at the log probability score recorded in those games in which they were involved, which we do in the table at right.

It reveals that WoSHBODS has done well at estimating win probabilities for games involving Melbourne, Adelaide, or Geelong, and less well at games involving Collingwood, Brisbane, or St Kilda.

In the case of the latter three teams - and only for those three - LPSs have actually been negative.

After only four rounds, of course, we need to be a little cautious about drawing broader conclusions.




On wagering, a fourth successive week of profit was, in part, prevented by a much more active Overs/Unders Fund that was responsible for -7.3% return this week. It should, in fact have been a positive return for that Fund but for my clumsy Excel work, which saw the Fund wagering in two markets it should never have been.

Anyway, as those of you who’ve followed me on the AFLM side for any period of time know, a bet made and published is a bet honoured here.

Overs/Unders betting aside, which accounts for only 5% of the Combined Portfolio, we can review the wagering performance of the two main Funds by making separate calculations for home versus away status, and favouritism versus underdog status, which we do in the table at left.

It reveals that the most lucrative wagering in terms of ROI has come from head-to-head wagering on home team underdogs and line wagering on away team favourites or away team underdogs.

Least lucrative has been line wagering on home team favourites, and head-to-head wagering on away team underdogs.

TEAM DASHBOARD

In the latest Ranking on Dashboard Metrics chart, the metric rankings currently most highly correlated with the competition ladder rankings are:

  • MoS Win Production Function: +0.99

  • % of Quarters Won: +0.94

  • Points Conceded and Goals Conceded: +0.93

  • Scoring Shots Conceded: +0.9

  • Q4 Performances: +0.89

  • Own Goals Scored and Own Points Scored: +0.87

  • Own Scoring Shots: +0.79

  • Own Scoring Shots Generated: +0.71

The metric least correlated is:

  • Q3 Perfomances: +0.25

And, lastly, below is the full extended version of the Team Dashboard.

It shows, among other things, that no team has won more than 13 of the 16 quarters they’ve played in, and that West Coast has won only two. It also shows that Adelaide have generated 11.3 more scoring shots than their opponents across entire games, including 6.8 of them in second halfs.

Also, Collingwood have scored 45% of their points in Q1s, but only 3% in Q4s, while also conceding 46% of the points that they have in Q4s.

In a similar vein, Carlton have conceded 47% of the points that they have in Q4s, and Fremantle 44% and Geelong 48% in Q3s. Melbourne have conceded only 4% of the points that they have in Q4s.

GWS and Collingwood have both also failed to kick a goal in Q4s, whilst Geelong has yet to concede one in Q1s and Melbourne in Q4s.