MAFL 2010 : Round 27 Results (GF 2.0)

If MARS Ratings are to be believed, the right team won on Saturday.

In winning so emphatically, Collingwood lifted its MARS Rating by 3.7 points to finish the season rated 1,055.4, which rates it above the Geelong of 2009 (1,044.5) but below the Geelongs of 2008 (1,065.9) and 2007 (1,058.3). Prior to that, the only teams with a higher end-of-season MARS Rating since 1999 were the Lions of 2002 (1,056.2) and the Dons of 2000 (1,072.7).

The following graphic shows the end-of-season ratings for every team over the seasons 1999 to 2010.

The Pies' victory more than recompensed all still-active Investors for what they lost last weekend. The Recommended Portfolio rose by 1.9% and finished the season down by just 5.1%, while MIN #017's Portfolio rose by 5.3% to end the season down by 40.1%. MIN #002's Portfolio, which was 100% weighted to the Shadow Fund, lost 28%.

(A final reconciliation of Fund performance uncovered a discrepancy of 0.7% in favour of the Recommended Portfolio. This has been reflected in the figure above.)

Both the Portfolios that were active during the Finals made money over these 5 weeks, as you can see in the following graphic.

Another couple of weeks of Finals and you have to wonder if the Recommended Portfolio might finally have broken through into profitability. If any of you are stock markets chartists you might have a view on this - please let me know.

A look at the round-by-round view for each Portfolio shows that it was Rounds 8 and 13 that did much of the damage to all Portfolios, though Round 20 also wasn't kind to MIN #002's Portfolio and MIN #017 could have done without Round 7.

Here's the final dashboard for 2010.

Four of the six MAFL Funds wound up making a profit this year,with ELO the best of them making almost 28%, followed by Heuristic-Based making a little over 21%. Then came Prudence, which returned almost 16%, and Hope, which made 2.5%. The two losing Funds were Shadow, which lost 28%, and New Heritage, which lost just over 40%.

We can decompose those performances in a number of ways, firstly by team wagered on.

Alternatively, we could look at Fund performance by team wagered against.

Averaging these two views gives us a way to estimate the contribution that each team has made to Fund (and Portfolio) performance across the season, whether we were hoping for the team to win or to lose.

New Heritage made money, in aggregate, on the games involving only six of the teams, losing money on the other 10. Games involving St Kilda caused the greatest losses, while games involving Hawthorn generated the greatest profit.

Prudence lost on 6 teams and won on 10, losing most heavily when West Coast was playing and winning most handsomely when Hawthorn were on the field. Hope also made most when Hawthorn were playing, but lost most heavily when the Cats took part.

Shadow lost most on Carlton and won most on Adelaide, while the Heuristic-Based Fund made most on Melbourne and lost most on West Coast. ELO-Line lost most on Geelong and won most on Melbourne.

In total, the Recommended Portfolio lost money on games involving any of 9 teams and won on games involving any of the other 7. St Kilda's contests were the most costly for this Portfolio, and Adelaide's were the most profitable.

Next, we turn to Margin Tipper performance. BKB recorded the season's best Mean Average Prediction Error (MAPE), finishing on 29.57 points per game, ahead of LAMP on 29.98 and HAMP on 30.10. Best Median APE was turned in by LAMP with 26.0 followed by BKB and ELO on 26.5.

Across the season's entire 186 games, ELO correctly predicted 121.5 or 65.3% of them, BKB and LAMP managed 118.5 (63.7%), HAMP scored 117.5 (63.2%), and Chi lumbered to 111.5 (59.9%).

Well, that's it for another season. I think I've run more analyses, written more blogs, and learned more about the patterns in footy data and how to display them this season than in any of the previous five. And yet, we still made a loss, which is my lone regret.

I'll almost certainly be going around again in 2011, though there's much work to be done in the off-season with the entry of a 17th team next year and the introduction of the bye. Work is well-progressed on moving MAFL to a website format next year; more on this in future months.

(If you want a sneak peek, it's here [Actually - it's not any more ...]).

Any blogs I write during the off-season will be written on the new site. Hope to see you there.

Investors: please e-mail me with details of what you want done with your Funds.

MAFL 2010 : Round 27 (or GF 2.0)

Every so often things crop up that unexpectedly test the statistical models I've constructed. For example a client will ask for a model to be used for a practical purpose such as forecasting, or they'll ask me to rerun a set of scenarios that I've created using a model, but this time with slightly different inputs.

What makes these situations a test for the models - and, I'll be honest, frequently a 'hold-your-breath-as-you-run-the-numbers' moment for me - is when there's an obvious way to validate the results using pure commonsense. Forecasts should look like a plausible extention of the actual time series that you modelled, and scenario outputs based on different inputs should usually differ from the earlier outputs you produced in logical ways.

Last week's drawn Grand Final, which meant that the MAFL Models faced the unprecedented situation of having to forecast the result for exactly the same matchup two weeks running, provided just such a test.

I'm pleased and not just a little relieved to report that, to my mind, the MAFL models have 'passed' by behaving sensibly - although in the case of the New Heritage Fund, that's a relative rather than an absolute assessment.

Both the New Heritage Fund and Prudence Funds, chastened a tad and accordingly recalibrated by the Pies' inability to win last week, have stuck with the Pies, now priced at $1.55, but have made smaller wagers. As well, ELO, which is based on MARS Ratings, now forecasts a slightly smaller win for the Pies, but a win still large enough to encourage ELO-Line to wager its customary 5% on the Pies giving 11.5 start.

(I should note that a minor glitch had me reporting ELO as tipping the Pies to win by 51 points last week. It should have been by only 40 points. This week the forecast margin is 38 points.)

Chi, HAMP and LAMP have also made only small but nonetheless downward revisions to their predictions of the Pies' victory margin. Some validation for their 2-4 point adjustments is provided by the corresponding change in the bookie's margin - by 5 points, from 16.5 to 11.5 points.

Here's the detail:

In short, everything's pretty much as it was last weekend, though we stand to collect more this weekend if the Pies win than we would have had they won last weekend, and we also stand to lose less this weekend if they don't.

For the sake of completeness I should let you know that, this week, line bets are inclusive of extra time. So, in the unlikely event that the Pies and Saints again finish level at the end of normal time, our line bet will not be lost at that point. If the Pies then go on to kick two goals clear of the Saints by the time the hilarity finishes ensuing, we'd collect - on all the bets as it happens.

Based on the Margin Tippers margin predictions, HAMP will finish the season with a sub-30 MAPE provided the final margin lies between a Saints win by 6 and a Pies win by 36 points, and LAMP will do the same if the Saints win by 33 or fewer, or if the Pies win by 59 or fewer. BKB will finish with a MAPE below 29.5 if the Saints win by 19 or fewer, or if the Pies win by 42 or fewer.

Lastly, here's the week's full Ready Reckoner:

And that definitely is the last pre-round MAFL blog for 2010.

MAFL 2010 : Round 26 Results (of a fashion)

After that it all feels a little flat.

I just assumed there'd be extra time on Saturday and at least an attempt to find a winner on the day; making 44 players, 2 coaching staffs, 100,000 spectators and countless fans go through that all again seems cruel, unusual and frankly unnecessary.

Anyway, there it is - we've a Round 27 this year and another set of potential wagers, and I've a chance to see how many of my spreadsheets and programming scripts will break when faced with an unprecedented 27th round.

Whilst the teams walked away from the weekend no worse off than they entered it, the same can't be said for Investors. Our line bet on Collingwood giving 16.5 points start was, of course, a losing one, and our head-to-head wager paid off at only half price, which for us on the Pies at $1.45 was just 72.5c in the dollar. As a result, the Recommended Portfolio dropped 1.3% and MIN#017's dropped 2.9%. However - and I didn't expect this cliche to get another run - there's always next week.

Here's the Dashboard for Round 26:

Collingwood dropped a bit over 1 point on MARS Ratings as a result of the weekend's non-result, but still maintain a lead over the Cats of about that same margin. A loss next weekend, or even a win by just 1 or 2 points, would see them finish the season behind the Cats on MARS Ratings.

The Pies' MARS Ratings loss was the Saints' gain. Their 1 point increase served to increase their superiority over the Dogs, which now stands at 4 Ratings points. The Saints have no hope of overhauling the Cats though and grabbing 2nd spot unless they can contrive to produce a string of draws that imperils the venuing for the Boxing Day Test.

Each of the top 3 Margin Tippers based on Mean Absolute Prediction Error (MAPE) knocked 0.07 points from their respective MAPEs this week, leaving the ordering of BKB, LAMP then HAMP unchanged but dragging BKB under 29.5 points per game, LAMP now comfortably under 30, and HAMP within 0.04 points of 30.

ELO was the only Margin Tipper whose Median APE changed - up 0.5 points to 27, relegating it to joint third with HAMP, behind LAMP and BKB on 26 and 26.5 points respectively.

See you all again next week.

MAFL 2010 : Round 26 (Week 4 of the Finals a.k.a The GF)

There'll be no dramatic last game plunge into profitability for any Investor this season.

The best that Investors with the Recommended Portfolio can hope for is to end the season down by about 4.5%, and it'll take a Pies victory in the GF by 17 points or more to deliver them that result.

Once again this week it's New Heritage, Prudence and ELO-Line that are the active Funds. Hope has made no wagers, making this the third week in a row that it's been on a wager strike. New Heritage has lobbed 10.5% on the Pies at $1.45, while Prudence has placed 4.7% on the same team at the same price. ELO-Line's taken the Pies for 5% at $1.90 giving 16.5 start.

Including these wagers, every dollar in the New Heritage Fund has now been wagered almost 9 times during the season. For the other Funds, the equivalent 'turn' figures are: Prudence just over 3 times, Hope just under 2, Shadow just over 3, Heuristic-Based exactly 5, and ELO just over 4.5.

In aggregate, then, every dollar in the Recommended Portfolio has been put at risk almost 4.4 times during the season. Given TAB Sportsbet's typical vig of around 6.9% on head-to-head markets and 5.25% on line markets, the expected loss for the Recommended Portfolio for the season was therefore around 30%. So, the Recommended Portfolio will lose quite a bit less than it 'should' have - but you can't pay bills, I know, with unexpectedly small losses ...

Here's the detail on the week's bets and tips.

Not only do we have unanimity amongst tipsters in their prediction of the Pies to win on Saturday, but we also have near-uniformity in their opinions about the size of that victory. Three of them tip Collingwood by 17, and BKB tips them by a margin as close to 17 as you can get when you're forced to tip half-point margins. ELO's the outlier, predicting the Pies to win far more comfortably - by over 8 goals. All Margin Tippers therefore expect the Pies to cover the spread - albeit narrowly and, of course, excluding BKB.

Given those margin predictions, HAMP will finish the season with a sub-30 MAPE provided the Pies win by between 9 and 25 points, and LAMP will do the same if the Saints win by 16 or fewer, or if the Pies win by 50 or fewer. BKB will finish with a MAPE below 29.5 if the Saints win by 1 or fewer, or if the Pies win by 34 or fewer.

Here's the week's Ready Reckoner:

Saturday will be the first time in a decade that 1st has met 3rd in the Grand Final. The last time this occurred was back in 2000 when the minor premiers in the Dons toppled the Dees. It'll also be only the fourth time in 12 years that a team from 3rd has made the Grand Final.

Here's a summary of the last 11 seasons' Grand Finals in terms of the ladder positions in which the participating teams finished the home-and-away season.

MAFL 2010 : Round 25 Results (Week 3 of the Finals)

As predicted, the haloed and the winged triumphed over the furry this weekend, leaving us with a Pies v Saints Grand Final for only the second time in VFL/AFL history.

Presumably there are supernatural consequences of cursing saints, but it was difficult to avoid risking them on Saturday night if you were a MAFL Investor watching the game as the Saints went marching off and allowed the Dogs to tack on just enough late points to win on line betting by half a point.

That cost the Recommended Portfolio almost 1% and meant that it increased by only 2.2% over the two games. This leaves the Recommended Portfolio down by 6.4% on the season on the back of three straights weeks of profitability during the Finals.

MIN#017's Portfolio also climbed for the third successive week, this time by 9.1% to leave it down by 42.4% for the season. MIN#002's Portfolio remained unchanged at 72c.

Here's the Dashboard for Round 25:

On MARS Ratings, the two weekend winners both swapped places with the losers, which slips the Pies into 1st and the Cats into 2nd, and the Saints into 3rd and the Dogs into 4th.

Once again all tipsters picked both winners this weekend. Chi and ELO recorded the best Mean Absolute Prediction Errors (MAPEs) of 15 points per game, while HAMP managed 18, BKB 20, and LAMP 21.5. These high levels of accuracy produced reductions in the season-long MAPEs for all Margin Tippers but left their ordering unchanged.

BKB remains 1st on 29.56 points per game, ahead of LAMP on 29.98 - the first time it's been below 30 since Round 19 - and HAMP on 30.11.

Surprisingly, neither HAMP's not LAMP's excellent MAPEs would have translated into line betting success this season. HAMP's only been 46% accurate in selecting the correct line winner and LAMP's only been 49% accurate. In comparison, ELO's been right almost 55% of the time.

The Median APE metric has been no better at predicting line betting performance, since LAMP retains outright leadership on this measure with a score of 26 points. ELO knocked half a point from its Median APE this week to draw it level with BKB on 26.5 points and in joint 2nd place.

What's been the source of ELO's superior line betting accuracy in comparison to HAMP, LAMP and Chi (his accuracy is only 47%)? Being right more often in those games that were closer in terms of line betting it turns out, as the following graphic shows.

The rows in this graphic are based on the size of the absolute handicap-adjusted margin - the number that you get when you subtract the away team score from the home team score, add the home team handicap and then take the absolute value. For example, the absolute handicap-adjusted margin for a game that finishes 100-75 where the home team was giving 30.5 points start is 5.5 points, which is the absolute value of 100-75-30.5.

In line betting terms, therefore, the closest games are those on the first row of the table, and games become less close as we move down the rows.

Each pie reflects two things:

• the proportion shaded black represents the accuracy of the particular Margin Tipper for games within the range of actual absolute handicap-adjusted margins described by the row
• the size of the pies within each row is proportional to the number of games that have finished with that particular range of actual absolute handicap-adjusted margins

Now focus on ELO's column. You can see that it's done well relative to the other Margin Tippers in those games that finished with an absolute handicap-adjusted margin under 24 points - in fact, it's the only Margin Tipper with a better than 50% record for these games - and that it's been particularly accurate in those games that finished with an absolute handicap-adjusted margin of 24 to less than 36 points.

In those games that finished with an absolute handicap-adjusted margin of 36 points or more, which have been the most frequent type of games this season, it hasn't been especially accurate, but no less so that the other Margin Tippers.

This week, in terms of home-and-away ladder positions, we saw 1st defeat 2nd and 3rd defeat 4th. Historically, teams from 1st and 2nd have now performed equally well in the 3rd week of the Finals, appearing 11 times each for 8 wins and 3 losses.

Teams from 3rd, however, have a much better record than teams from 4th, though they've appeared in the Semis on two fewer occasions. Third-placed teams now have a 44% record of proceeding to the Grand Final, while fourth-placed teams have only an 18% record.

MAFL 2010 : Round 25 (Week 3 of the Finals)

If you've been following the story so far and I were to tell you that there are two home-team favourites this weekend, one of them short-priced, you should be able to guess the behaviour of at least two of the Funds that are still trading.

New Heritage, of course, has taken a large piece of each favourite, which amounts to 7.7% on the Pies at $1.80, and 11.8% on the Saints at $1.25, while the Hope Fund is having none of either proposition.

Meanwhile, the two remaining, less predictable Funds in Prudence and ELO-Line have made one and two wagers respectively. Prudence has dropped 6.1% on St Kilda, while ELO-Line has outlaid 5% on each of Collingwood (-6.5 and at $2.05) and St Kilda (-24.5 and at $1.90).

Here's the detail on the week's bets and tips.

Once again this week the tipsters are, like a roof full of well-trained tilers, all pointing in the same direction.

Collingwood is the first unanimous tip and is predicted to win by between 1.5 and 17 points. (By the way, I've inferred the 1.5 point margin for BKB by using the rule that I discovered in this blog, which allows me to infer a handicap from head-to-head prices and vice versa.) Only Chi and ELO expect the Pies to cover the spread.

The Saints are the other unanimous tip, but in this game our Margin Tippers' agreement extends not only to the winner but also to the margin of victory. All five predicted margins lie within a 6 point range from 24 to 30 points. Only the low end of that range - Chi's 24-point tip - is less than the start that the Saints are being asked to give, so on that basis you'd have to like our line bet.

Here's the week's Ready Reckoner:

As I've noted previously, the Prelim Finals have been the almost exclusive province of teams from the top half of the top 8, as you can see from the following table, which summarises team performances based on their ladder position as at the end of the home-and-away season.

Of the twenty teams that have progressed to the Grand Final from the Prelims, two-thirds of them have been teams that finished either 1st or 2nd in the home-and-away season. This year, of course, we know that this tally will increase by only one, since we have 1st facing 2nd in one of the Prelim matchups.

This has happened on 5 occasions previously and the team from 2nd spot has prevailed in 3 of those 5.

In the other game we have 3rd playing 4th, which is another pairing that we've seen 5 times before. Across those clashes, the team from 3rd has won 60%.

MAFL 2010 : Round 24 Results (Week 2 of the Finals)

Maybe MAFL should only operate during the Finals.

The Cats and the Dogs delivered almost to order for MAFL Investors in their respective Semis, the only losing bet coming as a consequence of the Dogs falling just two points short of covering their 6.5 points spread.

This meant that the Recommended Portfolio rose by 2.2c to 91.49c and MIN#017's Portfolio jumped 7.65c to 48.46c. With no action this weekend MIN#002's Portfolio remained unchanged at 72c.

Here's a season-long, game-by-game view of each Portfolio's price:

(It's getting to that point in the season where some of the charts and tables I've been creating but not publishing are rapidly approaching their Best Before date; expect to see a few more of these in coming weeks ...)

Next, the Dashboard for Round 24:

There's been no change in team rankings based on MARS Ratings, though the Cats' 69-point victory over Fremantle has kicked them over 5 Ratings Points clear of the Pies, which, as you'll see in a future blog post describing the latest round of simulations, has the Cats as MARS favourites for the flag.

As well, the Dogs' victory over the Swans was just about large enough to preserve its MARS Rating, which leaves the Dogs still more highly MARS-Rated than the Saints. That's still not at all what the bookies think.

All tipsters picked both winners this weekend, with LAMP and BKB recording the best Mean Absolute Prediction Errors (MAPEs) at about 15 points per game. BKB's performance knocked 0.16 points from its season-long MAPE, which now stands at 29.66 points per game, still the best of all the Margin Tippers.

LAMP, which remains in 2nd, sliced 0.17 points from its MAPE, dragging it to the precipice of a 30 MAPE - it now stands at 30.07.

HAMP remains in 3rd on the MAPE metric, down 0.14 points per game this week to 30.25.

Only BKB saw its Median APE metric change this week, down by 0.5 point to 26.5 to give it outright second behind LAMP on 26 and ahead of both ELO and HAMP on 27.

The expected victories by the Cats and the Dogs continued the decade-long dominance of the teams from ladder positions 1 through 4 in Semi Finals. As the table below shows, these teams now have a 20 and 2 record in this week of the Finals.

MAFL 2010 : Round 24 (Week 2 of the Finals)

Each season as we enter the Finals and games take on heightened historical relevance, a part of me wishes that the MAFL Funds would sense the occasion and respond accordingly by doing something dramatic and memorable.

They never do, of course, partly because they're not sentient and partly because the opportunity for winning large sums of money on huge home-team underdogs rarely arises during the Finals. As far as the Funds are concerned, the Finals are just another round offering a few more opportunities to spot and exploit mispricing in the head-to-head and line markets.

And this, cooler heads might say, is probably as it should be. After all, $100 lost or won on a Finals game buys no more or less than $100 lost or won in Round 22. It just feels different to say during the off-season that, say. you won a lot of money on the Grand Final. Irrational, undoubtedly, but true nonetheless.

Anyway, to this week's fare. New Heritage, Prudence and ELO-Line are all lining up behind the home team favourites in both contests this week, while Hope has found the sub-$2.00 prices on offer for the Cats and the Dogs far too tame for it to risk its newly acquired profitable status. It's made no bets at all.

Here's the detail.

This week the unanimity is positively deafening, as all five remaining tipsters are, as the wagering Funds, predicting victories for the favourites. The tipsters believe the Cats will win by anything between about 4 and 10 goals, and, excepting ELO, that the Dogs will win much more narrowly, by only 1 or 2 goals.

ELO thinks the Dogs will win far more comfortably than this. On a few occasions in recent weeks I've commented on the Dogs' still-high MARS Ratings and it's this that has prompted ELO to tip the Dogs to win by over 7 goals.

Here's the week's full Ready Reckoner:

The second week of the Finals has been the last week for most teams who've entered it having finished in the bottom half of that season's final eight. Of the twenty such teams that have fit this description during the past 10 seasons only two have progressed to week 3: Hawthorn, who finished 6th in 2001 and who were eventually knocked out by the Dons in the 1st Prelim, and Collingwood, who finished 6th in 2007 and who went out to the Cats in the 1st Prelim of that season.

The particular matchups that we have this week in terms of ladder positions are 2nd v 6th and 4th v 5th. This first configuration has occurred once before, in 2000 when the 2nd-placed Carlton beat the 6th-placed Lions. The second configuration's been slightly more common. We've seen it three times before and, on each occasion, the team that finished 4th has emerged victorious. Most recently, we saw 2nd play 6th last season when Collingwood beat Adelaide, and before that we saw it in 2007 when the Roos beat Hawthorn, and before that in 2001 when Richmond defeated Carlton.

The chart below summarises the fate of teams from each of the 8 ladder positions in the first two weeks of the Finals (the Week 1 figures having been updated to include last week's results).

Everything then seems to point to the Cats and the Dogs going through. Time to get nervous.

MAFL 2010 : Round 23 Results (Week 1 of the Finals)

MAFL's generally done well during the Finals and, while it could have been better had the Cats' final goal been allowed to stand and had the Swans managed more than 3 behinds in the 3rd term, this year's September has at least started in the black.

Of the four Funds trading this week, all but the ELO-Line Fund made money. Hope's success added 5c to its price and lifted it into overall profitability for the season. That means that we've now only the New Heritage and Shadow Funds to blame for the season's losses.

For the Recommended Portfolio, these losses now amount to a little under 11% for the season after it rose 2% on the weekend. MIN#017's Portfolio also showed a small gain, rising by 2.3% to leave it down about 59% for the year. MIN#002's Portfolio is no longer trading and so remains down 28% on the year.

Here's the (truncated) Dashboard for Round 23:

Whilst there was only one change of ladder positions on MARS Ratings this week, the two sizeable victory margins did produce some numerically substantial changes in the Ratings themselves. Collingwood's 4.5 Ratings Point gain, coupled with Geelong's 1.8 Ratings Point decline, narrowed the Ratings gap between these two teams to about 1.5 Ratings Points, which is the smallest it's been since Geelong took over top spot from Collingwood in Round 20.

HAMP, ELO and Chi all correctly tipped 3 of the weekend's 4 winners, while BKB and LAMP both managed only 2 from 4.

Despite another relatively poor week's tipping, BKB remains as the only Margin Tipper with a sub-30 Mean Absolute Prediction Error. It's now on 29.8 points per game, ahead of LAMP on 30.24 and HAMP on 30.39.

Median APE measures were unchanged for all Margin Tippers this week, leaving LAMP leading on 26 points (not 26.5 points as indicated last week), a full point ahead of BKB, ELO and HAMP, all tied for 2nd on 27.

MAFL 2010 : Round 23 (Week 1 of the Finals)

The importance of the weekend's fixtures should have all of us curious about their outcomes. If you're a Recommended Portfolio holder, though, and you're a bit concerned that one or two contests might drift into dullness, be comforted by the fact that you've wagers in all four.

With the Shadow and Heuristic-Based Funds no longer active, only four Funds had decisions to make this week and each of them has found at least one game worthy of a flutter.

New Heritage likes the look of all four contests - which only further convinces me that, should I run this Fund again next season, I'll need to find a way to prevent it from wagering on the bye. Anyway, it has made four wagers totalling a little under 40% of the Fund, the largest for 11.9% on Collingwood at $1.25 and the longest-priced for 5.2% on Freo at $2.15. The weighted average price of all its wagers is $1.45.

ELO-Line has also made four wagers, its assortment totalling 20% of the Fund and including three wagers on favourites and one on the underdog Freo. Prudence has added four more with a weighted average price of $1.52, largest amongst them a 4.6% dollop on the Pies at $1.25 and the longest-priced on Freo at $2.15 for 2.8% of the Fund.

Hope rounds out the bakers' dozen of wagers for the Recommended Portfolio with a single bet of 4.4% on Freo at $2.15.

In total, the 13 bets made on behalf of the Recommended Portfolio total about 13% of the Fund.

MIN#017 is again forced to endure the recklessness of New Heritage's wagering style and so carries the burden of its four wagers this weekend.

Here's the detail, this week in a slightly modified form that includes the tips from those tipsters that are still active and Ready Reckoner-style information for the Recommended Portfolio.

In three of the contests the tipsters have all gone with the home team favourites, while in the fourth there's some conjecture, as Chi, ELO and HAMP have lined up behind Fremantle, the home team underdog, leaving LAMP and BKB on their own endorsing Hawthorn.

Here's the week's full Ready Reckoner:

The system used for the finals series in 2010 is the same one that the AFL has used since 2000 and is described in the following graphic (courtesy of Wikipedia):

For the first time, this year I've sat down and worked through what the finals system means for teams finishing in different ladder positions. In hindsight I suppose it was obvious - as most things are - but I was surprised by the relative difficulty faced by teams finishing 5th through 8th in securing a Flag.

In all likelihood such a team will need to win their week 1 final and then win a Semi-Final, Preliminary Final and Grand Final against three of the teams that finished in the top 4, as you can see in the following graphic, which shows the teams that each finalist could face in any particular week of the finals.

Testament to the difficulty faced by the teams finishing in the bottom half of the eight is the fact that none of them has made a Grand Final in any of the 10 seasons since we started using the current finals system.

In fact, in only two seasons - 2001 and 2007 - has a team from positions 5 through 8 even made it as far as the Preliminary Finals.

Focussing our attention now just on Week 1 of the finals, history suggests that the Cats and Fremantle should be heavily favoured to win, since teams in 2nd have defeated the 3rd-placed team in 9 of the 10 previous encounters, and teams in 6th have defeated 7th-placed teams with a similarly biased frequency.

Minor premiers have, on average, had more trouble with teams finishing 4th, winning only 60% of the time and, curiously, teams finishing 8th have won more often than they've lost in their Week 1 finals against 5th-placed teams.

MAFL 2010 : Round 22 Results

*Sigh*

Entering into Sunday with wagers on both favourites and a cumulative 3.7% profit on the weekend so far for the Recommended Portfolio, I had what I thought were reasonable hopes that this Portfolio would end the weekend having erased some of the loss it had accumulated over the preceding 6 months.

The Tigers and the Dees thought otherwise, however, and, combined, inflicted losses of over 6% on the Recommended Portfolio, eventually leaving it, writhing and in pain, down almost 2.5% on the weekend. This loss means that the Recommended Portfolio is now trading at about 87c.

MIN#002's and MIN#017's Portfolios also suffered losses - of about 4% and 6% respectively - driving them also further into the red.

(Nonetheless, I'll continue to post here as if I know something about football as long as you'll maintain the pretence with me.)

Here's the Dashboard for Round 22:

The Shadow and Heuristic-Based Funds are now closed for the season. It's interesting to note that, while both were successful in 70% of their wagers, Shadow lost 28c on the year while the Heuristic-Based Fund, which relied on Shadow's expertise for the first 12 rounds of the season, made 21c. Which goes to show that, in gambling, it's not just how often you win, but how much you make when you do and how much you lose when you don't. Now there's a homily you can take to the bank.

Tipping proved moderately difficult this weekend, partly because only five favourites were successful. This produced a lowish average of 4.77 correct predictions from 8 for the MAFL Tipsters. Best amongst our bunch were Consult The Ladder, Ride Your Luck, and Follow The Streak, which all tipped 6 from 8, a performance that, in Follow The Streak's case, was enough to secure it victory in the MAFL Tipping competition with a season-long score of 116/176 (66%).

Follow The Streak's strategy can be explained very simply: in any game pick the team that has the longer winning streak and, if both team's streaks are equal in length, pick the team higher on the ladder. Simple and - this year, at least - effective.

Second position was secured, jointly, by Consult The Ladder and Silhouette on 114 from 176 (65%). BKB finished five tips behind Follow The Streak and in equal 3rd-last on the MAFL Tipping ladder. Its score of 111 is six tips worse than the 117 it scored in season 2009.

Further evidence of the relative difficulty of tipping this year is provided by a comparison of this year's winning score - 116 - with that for 2009, when Silhouette led all MAFL Tipsters with a score of 124. In fact, Follow The Streak's 116 would have only placed it 7th last season.

I hope this comparison provides you with some small comfort if you also found tipping this year to be more than usually difficult.

Level-stake wagering on the tips of the MAFL Tipsters whenever they predicted a home team win would have been profitable over the season had it been applied to any but the tips of ELO, BKB and Chi, and would have been most profitable had it been diligently followed in relation to the prognostications of Easily Impressed I (who, virtually every week, has merely tipped the team that won by the largest margin, or lost by the smallest margin, in the immediately preceding round). Thumbs up, I think, for rules of thumb.

Not much changed this week in terms of team rankings on MARS Ratings, the sole movement being the trading of 6th and 7th spots between Sydney, who claimed 6th, and Carlton, who surrendered it.

That leaves the MARS rankings for teams somewhat different from their final competition ladder positions, most notably for Adelaide (ranked 8th on MARS but 11th on the competition ladder), Fremantle (9th on MARS, 6th on the competition ladder), and Port Adelaide (13th on MARS, 10th on the competition ladder). Hawthorn is the other team with a difference of two or more places in their respective MARS and competition ladder rankings: they're 5th on MARS but 7th on the competition ladder.

In the end, BKB was the only Margin Tipper to break the magical 30 for its Mean Absolute Prediction Error. Its 29.9 points per game saw it finish about 0.4 points per game ahead of LAMP. HAMP's strong showing in Round 22 was enough for it to snatch 3rd spot from ELO.

LAMP, meantime, as well as grabbing 2nd on Mean APE, held on to win the Median APE competition with a score of 26.5 points, 0.5 points ahead of BKB, ELO and HAMP, all tied for 2nd.

HELP predicted 4 from 8 line results this week to finish the season on 83 from 176 - comfortably sub-naive - and recorded similarly unsatisfactory probability scores. That'll be the last you'll be seeing of the HELP algorithm.

The Super Smart Model (SSM) tipped the first four line results for the round, but followed up with none of the remaining four. It also bagged 5 from 8 on head-to-head tipping. That left it with an impressive season-long line betting record of 98 from 176 (55.7%) and head-to-head record of 111 from 176 (63.1%), the same as BKB's. It's fairly certain you will be seeing more of SSM next year.

Lastly, the Bookie Probability Model had two successful and one unsuccessful wager this week, which netted out to a virtual breakeven position for the round. Over the course of the season, it would have made a quite substantial profit, and so it too will almost certainly return in 2011.

In the coming weeks I'll probably provide some more analysis of the 2010 home-and-away season, but for now, that'll do. 

MAFL 2010 : Round 22

So we've reached the end of the home-and-away season with much still to do if Investors are to finish the season showing a nett gain. A perfect set of results this weekend would drag the Recommended Portfolio narrowly into profit, but similar good fortune would not be enough to do the same for MIN#002 or MIN#017; they'll also need favourable results throughout the final series to finish ahead.

This week, the Recommended Portfolio has 25 bets and action in seven of the eight games, the Hawks v Pies game being the only game in which no money will change ownership. Most wagering activity has come from the always-active New Heritage Fund, whose six bets this week represent just over one half of the Fund. The weighted average price for these wagers is $1.42, the largest is 13.5% on the Cats at $1.01 (yes, $1.01), and the longest-priced is 0.7% on Adelaide at $2.65.

Prudence is next most active having ventured six wagers of its own for 21.5% of its Fund. The weighted average price for these bets is $1.49 and the two largest wagers are 5.8% on Geelong at $1.01 and 5.8% on the Dogs at $1.20. Its longest-priced wager is also on Adelaide at $2.65 and is for 1.7% of the Fund.

ELO has made five wagers, though it had to wait until after 5:30pm on Thursday to make them since TAB Sportsbet only posted line markets around then, presumably because their bookie was awaiting the team announcements. The unusual timing for the posting of these markets -and the fact that I've had the day in bed drifting in and out of sleep on account of a stomach bug - meant that I missed the initial prices on offer and so only secured the Dogs at $1.85 rather than $1.90. Amongst ELO's five wagers is one on the Cats offering 72.5 points start, which is amongst the largest starts I've ever seen on AFL line betting. The risk of the Cats leading by, say, 10 or 11 goals late in the match and then cruising into the final siren looms large.

Shadow has made three wagers - its last three for the season as it will not trade during the Finals - and these total 15% of the Fund and carry a weighted average price of $1.75. The longest-priced wager is for 5% on Brisbane at $3.05. Hope also has three wagers, its trio totalling about 11% of the Fund and carrying a weighted average price of $2.23, this average inflated by its largest and longest-priced wager of 5.2% on Adelaide at $2.65.

The Heuristic-Based Fund, also in its last week of trading, is the quietest Fund this week, making just 2 wagers for 10% of the Fund at a weighted average price of just $1.11. Its longest-priced wager is for 5% on the Dogs at $1.20.

Hope's three wagers represent MIN#002's weekend action, and New Heritage's six are MIN#017's.

Here's the detail:

For the Recommended Portfolio, the Melbourne v Roos game offers maximum upside (+3.2%), the Geelong v West Coast game carries maximum downside (-5.9%), and the Dogs v Essendon game has the largest swing between best- and worst-possible results (7.1%).

MIN#002 would gain most from a Brisbane victory over the Swans (+10.3%).

MIN#017 will see his best result if Melbourne defeat the Roos (+6.0%), his worst result if Geelong are beaten by the Eagles in what would be the shock of the season (-13.5%), and faces the largest swing between possible results of 14.7% on the Richmond v Port game.

Here's the Ready Reckoner:

There's unanimity amongst the MAFL Tipsters for only one game this weekend, though in three more games there's only token dissent from one or two tipsters. Across the eight contests the average number of dissenting MAFL tipsters per game is a low 3.1.

Here are the details:

• Fremantle are 9-6 favourites over Carlton. The Margin Tippers are 4-1 in support of Freo, with ELO the only dissenter. It tips the Blues to win by just 2 points, making this one of its Games of the Round. Predicted victory margins range from Carlton by 2 to Fremantle by 14 points. The five best-performed MAFL Tipsters - Easily Impressed II, Follow The Streak, ELO, Silhouette and Short-Term Memory II) favour a Blues victory by 3-2.
• Geelong are the week's only unanimous favourites. They play the Eagles and are expected by the Margin Tippers to win by between 16 and 73 points.
• Collingwood are 13-2 favourites over Hawthorn, and the MAFL Tipsters are unanimous in tipping the Pies. They predict victory margins for them ranging from just 6 to 18 points, however, so their confidence is not all that great. The Top MAFL tipsters are also unanimous in selecting the Pies.
• St Kilda are 14-1 favourites over Adelaide. The Margin Tippers all tip St Kilda, and do so by margins of between 4 and 15.5 points. Chi tips St Kilda by just 4 points, making this his Game of the Round. The Top MAFL tipsters are also unanimous in their support of the Saints.
• Sydney are 11-4 favourites over the Lions, with the Margin Tippers unanimously tipping the Swans by margins between 6 and 20 points. The Top 5 tipsters also favour Sydney, but only by 3-2.
• The Dogs are 14-1 favourites over Essendon, and are unanimously tipped by the Margin Tippers, with predicted margins of between 16 and 53 points. The Top tipsters are also unanimously predicting a Dogs victory.
• Port are 10-5 favourites over the Tigers, though 4 of the 5 tipsters siding with the Tigers are amongst the Margin Tippers. ELO is the holdout, tipping Port by 2 points, making this its second and final Game of the Round. Predicted margins for this game range from Port by 2 to Richmond by 16 points. The Top 5 tipsters unanimously predict a Port victory.
• The Roos are 9-6 favourites over Melbourne. The Margin Tippers favour the Dees 3-2, with HAMP (Roos by 3), LAMP (Dees by 4) and BKB all having this as their Game of the Round. Predicted margins range from the Roos by 3 to Melbourne by 8. The Top 5 MAFL Tipsters favour the Dees 3-2.

The Super Smart Model agrees with only three of the five ELO wagers this week, disagreeing that the Cats will cover the 72.5 point spread and that the Dogs will cover their 28.5 points spread. Indeed, ELO's wager on the Cats was a near thing - had the Cats been giving another 1 point start ELO would have agreed with SSM and felt that the start was too great.

Here's SSM's view of the entire round:

SSM's head-to-head tips are for the eight favourites this week, though it predicts that six of these favourites will prevail by 2 goals or less.

The Bookie Probability Model (BPM) is convinced that the TAB Sportsbet bookie is offering value on three home teams this week and so recommends a 4.2% wager on the Crows, an 11.1% wager on Brisbane, and a startling 22.4% wager on the Dogs. BPM's probability estimates are heavily influenced by MARS Ratings, so this large suggested wager on the Dogs is a consequence of the disparity between the bookie's and MARS' view of the Dogs overall quality, which is an issue we've addressed in earlier blogs.

Lastly, the HELP line predictions, for what they're worth:

MAFL 2010 : Round 21 Results

Teams, I suppose, finish last for a reason.

And so it was with the Eagles on Sunday afternoon, who appeared to be oblivious to the importance that most MAFL Investors were placing on the outcome of their clash with the Roos. Going into that game, Investors with the Recommended Portfolio were up by about 1.3% on the round and only needed a win by the Eagles - or, worst case, a loss by 6 points or fewer - to finish the weekend in the black.

But the Eagles couldn't land the result, so the Recommended Portfolio finished down by about 0.5%, leaving that Portfolio down by a smidgeon over 10% on the season, with time very rapidly running out.

MIN#002's Portfolio managed a very small gain, rising by 0.6% to finish the weekend down just over 24% on the season. The MIN#017 Portfolio was not, however, as lucky, and shed almost another 7% this weekend, ending down by over 55% on the season.

Herewith, the latest Dashboard:

Amongst the losses, the Heuristic-Based Fund managed to spin a profit, thereby ensuring that Short-Term Memory I will retain control of it for the final round of the home-and-away season.

Moving next to tipping we find that we've a new leader on the MAFL Tipping Ladder. It's Follow The Streak, whose 6 from 8 took it to 110 from 168 (66%) for the season, leaving it one tip ahead of ELO, Silhouette, Easily Impressed II and Short-Term Memory II. The best performances came from Easily-Impressed I and Short-Term Memory I, each of which picked 7 of the 8 winners. BKB managed only 5 and still languishes 4 tips from the leader.

On average, the MAFL Tippers scored 5.15 correct tips each.

Four pairs of teams changed positions this week on the MARS Rating table: Hawthorn and Carlton swapped 5th and 6th, Adelaide and Fremantle swapped 8th and 9th, the Roos and Melbourne swapped 10th and 11th, and Port and Essendon swapped 13th and 14th. This leaves Adelaide in 8th on MARS with a rating of around 1,000, despite lying 12th on the competition ladder. This would suggest that they've had, in hindsight, a relatively tough draw.

Fremantle, meantime, sit 6th on the competition ladder, but 9th on MARS Ratings.

For the sixth successive round Mean Absolute Prediction Errors (MAPEs) generally rose. BKB still holds the lead on this metric and is now on 30.5 points per game, while LAMP (30.95) has reclaimed 2nd spot from ELO (31.06).

ELO and HAMP's Median APEs both rose this week. LAMP retained 1st position on 26.5 points, a whole point ahead of BKB and HAMP who now share 2nd.

HELP predicted just 3 from 8 line results this week, and was comprehensively out-tipped by the Super Smart Model, which snagged 7 from 8 (along with 6 from 8 on head-to-head tipping).

The Bookie Probability Model lost its only wager, which was 5% on Carlton. That leaves it up, notionally, by only 133% on the season. If only ...

MAFL 2010 : Round 21

The AFL contend that the Cats are taking on the Blues at home this Friday night. I contend that it's the Blues that are taking on the Cats at home.

When I made the decision to deem this game a Blues home game over 6 months ago, I had no idea quite how important it might prove to be for MAFL Investors. As a direct consequence of that decision, all but the New Heritage Fund were permitted only to wager on the Blues, and forbidden to wager on the Cats. Four of the Funds have taken this opportunity, which means that many Investors now own a large, egg-laden basket named "Carlton".

All told the Recommended Portfolio has 28 bets up for adjudication this weekend, and these total about 28% of the Fund. A quarter of those wagers are due to the New Heritage Fund - though it's the only Fund not wagering on the Blues - and these total over 60% of that Fund and carry a weighted average price of $1.37. The largest is 13.3% on Collingwood at the disturbingly short price of $1.03, and the riskiest is 6% on Port at $2.

The Heuristic-Based Fund is the next most active Fund, with Short-Term Memory I instructing it to place 6 wagers totalling 30% of the Fund at a weighted average price of $1.99. The riskiest of these is 5% on Carlton at $4.50.

Three other Funds have each made four wagers. Prudence's four total just over 20% of the Fund and have a weighted average price of $1.17. The largest bet is 6.6% on St Kilda at $1.08 and the riskiest is 1.5% on Port at $2. Shadow's another of the Funds with a quartet of wagers. Its four total exactly 20% of the Fund and sport a weighted average price of $2.15. It too has 5% on the Blues.

ELO also has four bets, each of 5%. Three of the four wagers are on teams receiving start -though two of these teams are receiving the minimum possible 6.5 point start and one of them is priced at $1.80 rather than the usual $1.90, so you could only call one of ELO's teams a genuine outsider.

Hope has only three bets, totalling 14% of the Fund, but they're at a weighted average price of $3.09, this average dragged up by a 6.1% wager on the Blues.

MIN#002 has these three Hope wagers as his weekend's action and MIN#017 has New Heritage's seven.

Here's the detail:

For the Recommended Portfolio, maximum upside - quite obviously - is tied to the Blues v Cats game (+10%), while maximum downside attaches to the St Kilda v Richmond matchup (-5.9%). The largest swing between best- and worst-possible results is also associated with the Blues v Cats game (13.2%).

MIN#002 also stands to gain most from a Blues victory (+17.5%).

MIN#017 will see his best result if West Coast beat the Roos (+6.2%), his worst result if Collingwood go down to Adelaide (-13.3%) and faces the largest swing between possible results of 14.6% on the Hawks v Freo game.

Here's the Ready Reckoner:

Whilst the Recommended Portfolio's array of wagers superficially looks balanced, this 'balance' is only achieved by the significant upside in the Blues v Cats game, roughly counter-balanced by the moderate downside in four other games and smaller downside in the remaining three.

I'm not sure that we should be relying on significant upsets to occur in Round 21 of the season, but that's what Investors with the Recommended Portfolio are faced with nonetheless.

To tipping then, where we find that the outcome of six of the contests is highly debated and that there's unanimity for the other two. The average number of dissenting MAFL tipsters per game is a high 4.25.

Here are the details:

• Geelong are 8-7 favourites over Carlton. The Margin Tippers are 5-0 in favour of the Cats and predict victory margins ranging from 19 to 30.5 points. The six best-performed MAFL Tipsters - Easily Impressed II, Follow The Streak, ELO, Silhouette, Consult The Ladder and Short-Term Memory II) are split 3-3.
• St Kilda are unanimous favourites over Richmond, the second week in a row that Richmond have been universally shunned by the MAFL tipsters. The Margin Tippers predict Saints victory margins of between 37 and 57 points.
• Hawthorn are 9-6 favourites over Fremantle. Once more the MAFL Tipsters are unanimous in their support and here they predict victory margins ranging from 12 to 38 points. The Top MAFL tipsters are split 4-2 in favour of Freo.
• Collingwood are unanimous favourites over Adelaide. The Margin Tippers tip the Pies by between 21 and 52.5 points.
• The Dogs are 10-5 favourites over the Swans, with the Margin Tippers split 4-1 in favour of the Dogs, LAMP the holdout tipping Sydney by 2 and having this as its Game of the Round. The largest predicted margin of victory by the Dogs is 17 points. The Top 6 tipsters favour the Dogs 5-1.
• Port Adelaide are 10-5 favourites over Melbourne, though the Margin Tippers favour the Dees 3-2. Chi tips Melbourne by 2, ELO Melbourne by 3, and HAMP Port by 1, making this the Game of the Round for all these tipsters. The Top 6 tipsters are also torn: they're split 3-3.
• Essendon are 9-6 favourites over the Lions, with the Margin Tippers unanimous in selecting the Dons, in this game by margins of between 5 and 15 points. The Top 6 tipsters are again split 3-3.
• The Roos are 10-5 favourites over West Coast. The Margin Tippers favour the Roos 3-2, and BKB has this as its Game of the Round. Predicted margins range from the Roos by 5 to West Coast by 6. Five of the Top 6 tipsters pick the Roos.

The Super Smart Model agrees with three of the four ELO wagers this week, disagreeing only with ELO's belief that 43.5 points start for Richmond won't be enough. SSM reckons that Richmond need another point.

Here's SSM's view of the entire round:

SSM's head-to-head tips are consistent with the majority opinion of the MAFL Tipsters except for the Dogs v Swans game, where SSM likes the Swans, and the West Coast v Roos game, where SSM favours the Eagles in a tight one.

With a hint of solidarity, the Bookie Probability Model recommends just one wager this week: 5% on Carlton. Even if the Blues don't win this weekend, I think it's fair to say that the MAFL Funds, as a whole, saw value in them at $4.50.

Lastly, the HELP line predictions.

Julia +10.5 Seats

Julia Gillard's in an unusual position this weekend. She can take either side of a wager and probably be happy whether it wins or it loses.

You too can participate in the wager, but it requires that you weigh up the relative merits of an incumbent and a wannabe Prime Minister alongside those of two footy teams vying for positions in the 8.

Perplexed? Well here are two bets that TAB Sportsbet are currently offering:

So, one way or another, Julia's team wins the bet.

It's a mystery to me how anyone could sensibly go about framing a market for this wager, but I guess TAB Sportsbet are hoping that the smart money will know a lot about psephology or a lot about footy, but not a lot about both.

To provide you with just a little of the data you might want if you're considering a wager in this most exotic of markets:

• Labor currently holds 83 of the 150 seats in the House of Representatives, the Libs hold 55, the Nats 10, and Independents hold 2. So, if nothing changes, a line of ALP +10.5 gives the ALP 93.5 somethings (adjusted seats? footy-equivalent seats?)
• The Dogs have averaged just under 100 points per game this season and scored 101 points when they last played the Swans, at Manuka in Round 8. So, without adjusting for the fact that the Dogs are playing the Swans and are playing away, a line of Dogs -10.5 is likely to be something around 89.5 somethings

So, if the Dogs kick one goal more than their expectation or if Labor drop a goal's worth of marginals then the line bet favours the Dogs.

Me, I'll not be venturing a wager. I know that footy's hard to model; politics, I reckon, is nigh on impossible.

MAFL 2010 : Round 20 Results

Meh.

It's weekends like this one that make me remember a conversation that took place between two of my then team-members outside my office one morning some years ago when things were busy and nerves were generally a little frayed.

One team member, arriving at the desk of the other and clearly unhappy about something that had come to his attention in the last 12 milliseconds or so - the approximate time I imagine it had taken him to traverse the distance between his desk and his colleague's - felt obliged to 'share' his unhappiness with the desk's owner who patiently listened for about a minute and then delivered this gem, part parental, part 'get a grip': "Calm down. Nobody's died; nobody's been hurt".

And so it was this weekend for MAFL Investors, though a few might well feel that their chances of a profitable season did die at least a little over the course of proceedings.

All told, the Recommended Portfolio shed 7% to be down by just under 10% on the season, and MIN#002's Portfolio dropped 11.5% to be down by almost 25% on the season. MIN#017's Portfolio fell least of all, by just 0.1%, but is still down by almost 50% on the season and must surely now have chances for attaining profitability roughly equal to the chances of West Coast avoiding the Spoon.

Whilst five results contributed to the loss suffered by the Recommended Portfolio, I hold Freo and the Lions most culpable for the outcome. Together, their losses meant the difference between an increase of a couple of percent and the Fund's eventual 7% loss, and both teams had ample opportunity to win the games that they ultimately lost.

Anyway, here's the latest Dashboard:

That's now two weeks of losses in a row for the Heuristic-Based Fund, so another loss in Round 21 would see Short-Term Memory cede control of the Fund to another heuristic for the final week of the home-and-away season. At this point Easily Impressed I would be that heuristic as it has the best season-long level-stake home team only wagering performance.

Enough talk of wagering and loss, let's move on to MAFL Tipping.

Easily Impressed II scored just 4 from 8 this week, but that was enough to for it to hold outright 1st on the MAFL Tipping table. It's now on 105 from 160 (66%), one tip ahead of Consult The Ladder (which recorded 7 from 8, the week's best result), ELO, Follow The Streak, Silhouette, and Short-Term Memory II. BKB scored 6 from 8 this week but still finds itself four tips off the pace.

On average, the MAFL Tippers scored 4.69 correct tips in Round 20, which is about 0.2 tips better than their collective performance in Round 19.

Only four teams changed positions on the MARS Rating table. Geelong grabbed 1st spot from Collingwood, despite both teams winning handsomely in their respective encounters. Geelong, however, defeated a 1,040+ rated team, while the Pies trounced a team rated around 977, so the similarly-sized victory margins were quite rightly differentially rewarded in terms of MARS Rating points. Both teams are now rated the highest they've been all season.

Sydney and Freo were the other teams to swap MARS positions, with Sydney's victory over Freo being enough to propel them ahead of Freo and into 7th spot on the MARS ladder.

Season-long Mean Absolute Prediction Errors (MAPEs) took another beating this weekend, so much so that, for the first time this year, all Margin Tippers have MAPEs above 30. BKB retains the lead on the MAPE measure, however, and ELO is now 2nd having moved ahead of LAMP by dint of going backwards more slowly.

Median APEs were for the most part unaffected by the weekend's result, the only exception being LAMP's Median APE, which rose by half a point. Nonetheless, LAMP still leads on this metric, with HAMP and ELO still sharing 2nd.

HELP recorded its worst line-betting result of the season, correctly predicting just 1 from 8 results - a performance which, I can hear my Dad proclaim, "You couldn't do if you tried". (Of course if you could achieve this result intentionally, you'd be far better flipping your predictions and bagging 7 from 8, so the point here is probably moot, but never mind.)

To complete the tale of woe, SSM fared little better on line tipping, scoring just 2 from 8, and even our only notionally wagering model, the Bookie Probability Model, would have lost money this weekend, despite landing two of its three wagers. SSM did though manage 6 from 8 on head-to-head tipping.

MAFL 2010 : Round 20

How nice it is to be at this late stage of the season and still have six of the eight games with some effect on the composition of the final 8.

The Port v West Coast and Brisbane v Adelaide matchups are the two exceptions - though mathematically even Port and Adelaide still have the faintest glimmer of a sliver of hope (if you believe the results of my simulations in an earlier blog, which estimated them both as about 1,000/1 chances to snatch 8th).

As attractive as the games are from a spectating vantage point, they're also quite attractive from a wagering perspective, or at least they are as far as the Recommended Portfolio is concerned, which has put more than 20% of the Portfolio at risk for the fifth successive round.

This total comes from 28 individual wagers, five from all the Funds except Prudence, which has placed only three bets.

New Heritage's five bets represent the largest proportion of any Fund at risk (31.5%), though at a weighted average price of $1.53 they also carry the least risk. The largest wager from New Heritage is 11.4% on Carlton at $1.30 and the riskiest is 0.7% on West Coast at $2.80.

Shadow and the Heuristic-Based Funds have exactly the same wagers this week, which total 25% of the respective Fund and which have a weighted average price of $1.63. For both Funds the riskiest wager is 5% on the Dogs at $2.10.

ELO's five wagers also sum to one quarter of the Fund. Three are on underdogs and two are on favourites. The wager on the Dons was something of a surprise since, based on their head-to-head price, I expected them to receive only 39.5 points start not 41.5, which was the minimum start at which ELO would consider a wager on the home team.

Hope's five total 21% of the Fund but carry the extraordinarily high weighted average price of $3.76, due mainly to a 6.4% wager on the Dons at $6.25 and a 5.9% wager on the Roos at $3.75. This Fund has become progressively more active over the past five rounds, wagering 9%, 11%, 16%, 19%, and now 21% across these rounds.

Prudence's three bets are for about 9% of the Fund and have a weighted average price of $1.53. The largest and riskiest of the three bets is 4.1% on the Hawks at $1.68.

MIN#002, as always, has the Hope wagers as his weekend worry and MIN#017 is similarly burdened with New Heritage's impetuosity.

Here's the detail:

For the Recommended Portfolio, maximum upside is vested in the Essendon v Collingwood game (7.2%). This game also represents the largest swing between win and loss (9.0%), while the Carlton v Richmond game carries maximum downside (4.9%) for this Portfolio.

MIN#002 has most to gain if the Dogs beat the Cats (5.5%) and also faces the largest swing (10.5%) from this same game.

MIN#017 wants the Hawks to beat the Dees, since this carries a 5.8% upside, and for Carlton to beat Richmond, as this avoids an 11.4% loss. Two games carry almost exactly the same swing (14.8%) for this Portfolio: Carlton v Richmond and Fremantle v Sydney.

Here's the Ready Reckoner:

If the Recommended Portfolio were to lose its first three wagers this weekend it would need the remaining five results to be favourable if it were to (almost) breakeven on the round. Let's hope it doesn't come to that.

In my never-ending quest to find a way of summarising the implications of the result of each game on profitability, here's another attempt:

Each block represents the profitability that would result for the Recommended Portfolio from the outcome of the eight games. The greener the block, the greater the profitability, and the redder the block, the larger the loss.

At the top and sides of the chart are labels of the form nX - where n is a number from 1 to 8 and X is the letter A, B or C - which designate the outcome of a particular game. So, for example, the block under the 1A heading are the possible returns that would ensue if Essendon were to win on Friday night. (The mapping of codes to games appears at the base of the chart). As the weekend progresses, the relevant patch of possible outcomes will shrink until, eventually, one remains, that being the one pertaining to the eight results we've witnessed.

You can see immediately from this chart how important a Dons victory is for the profitability hopes of the Recommended Portfolio. If the Dons win then we'll spend the remainder of the weekend bouncing around in the lefthand third of the chart, which is mostly veldt-like in its greenness.

If, instead, the Dons were to lose head-to-head, but win on line betting, then our weekend will be confined to the semi-arid middle third, and if the Pies were to win and cover the spread then we're faced with an equally unappealling weekend in the righthand third.

Were the first three results to go 1C, 2C, 3B then we'd be destined to finish somewhere in the three rightmost columns none of which contains a patch of green.

Anyway, on to tipping, about which there's much less divergence of opinion this week, though there's unanimity in only one game. The average number of dissenting MAFL tipsters per game is only 2.5.

Here are the details:

• Collingwood are 14-1 favourites over Essendon. The Margin Tippers are 5-0 in favour of the Pies and predict victory margins ranging from 11 to 41.5 points. The four best-performed MAFL Tipsters - Easily Impressed II, Follow The Streak, Silhouette and Short-Term Memory II) all tip the Pies.
• Carlton are unanimous favourites over Richmond, with the Margin Tippers predicting victory margins of between 17 and 39 points.
• Fremantle are 12-3 favourites over the Swans. Once more the MAFL Tipsters are unanimous in their support. Predicted victory margins range from 9 to 20 points. The Top MAFL tipsters are split 3-1 in favour of Freo, the holdout being Follow the Streak, which prefers Sydney's 1 in a row to Freo's none.
• The Dogs are 12-3 favourites over Geelong, though for this game the Margin Tippers are divided in their support, three opting for the Dogs and two (BKB and HAMP) siding with the Cats. Predicted margins range from Geelong by 2 - assuming that the bookie's $1.75 price for the Cats implies a notional 1.5 points start - to the Dogs by 8. Four of the Margin Tipsters have this as their Game of the Round: HAMP, tipping Geelong by 2; LAMP, tipping the Dogs by 4; Chi, tipping the Dogs by 6; and ELO, tipping the Dogs by 8. The Top 4 tipsters all tip the Dogs.
• Port are 14-1 favourites over the Eagles, and all five Margin Tippers are supporting Port. They predict victory margins of between 10 and 26 points. The Top 4 tipsters all side with Port too.
• Brisbane are 12-3 favourites over Adelaide, with all but ELO amongst the Margin Tippers predicting a Lions victory. Margin predictions range from Adelaide by 7 to Brisbane by 12 points. The bookies have Brisbane at $1.80, making this BKB's Game of the Round. The Top 4 tipsters are split 3-1 on this game, Silhouette being the lone dissenter tipping a Crows victory.
• Melbourne, facing the Hawks, are the narrowest of favourites, garnering support from eight of the 15 tipsters. All five Margin Tippers predict the Hawks will win, by margins between 6.5 and 19 points. The Top 4 tipsters all favour the Dees.
• St Kilda are 13-2 favourites over the Roos. The Margin Tippers favour the Saints 4-1, Chi being the holdout tipping the Roos. Predicted margins range from the Roos by 17 to the Saints by 22. In Chi's defence he is on new medication for his heart murmur this week, so perhaps it's clouded his judgement. (Unfortunately, this excuse doesn't really work retrospectively, so you'll have to come up with your own ideas to explain the other 19 rounds of his tips.) The Top 4 tipsters are unanimous in their support of the Saints.

The Super Smart Model agrees with just three of the five ELO wagers this week, the first three as it happens, leaving them at odds on the line results for the Melbourne v Hawthorn and St Kilda v Roos games.

Here's SSM's view of the entire round:

SSM's head-to-head tips are consistent with the majority opinion of the MAFL Tipsters except for the Dogs v Cats game, where SSM likes the Cats, and the Melbourne v Hawthorn game, where SSM favours the Hawks, albeit narrowly.

The Bookie Probability Model recommends three wagers in the round: 6.3% on Carlton, 6% on the Dogs, and 0.5% on Hawthorn.

Lastly, the HELP line predictions.

MAFL 2010 : Round 19 Results

The only conclusion that a reasonable person could reach is that the Recommended Portfolio, concerned about causing undue alarm, has determined the best way to prepare the TAB Sportsbet bookie for its eventual profitability is to do so very, very slowly.

After Friday night's game, in which the Dons capitulated to the Blues and failed to protect their 6.5 point start, the Recommended Portfolio was down by about 1.5%. Then, over the course of Saturday the Portfolio essentially marked time, nudging the deficit for the weekend up only a fraction, so that Investors went into Sunday still down, now by about 1.4%.

Sunday started perfectly, with the Saints and Melbourne both winning and covering their respective spreads, leaving it all to the Crows, whose desperation for a spot in the eight should surely have been enough, to finally drag the Portfolio into profit. But the Crows fell 8 points short, leaving the Recommended Portfolio up by just 1.2% on the weekend, and still 2.9% short of breakeven for the season.

MIN#002 also made a profit (3.4%), leaving his Portfolio priced at around 87c, and MIN#017 saw his Portfolio rise by 4.1% taking his Portfolio price above 50c for the first time since Round 15.

Here's the latest Dashboard:

Usually the best and worst MAFL Tipster performance span a range of two, maybe three, tips. This week they span five, from Silhouette's seven to Easily Impressed I's two.

Silhouette's performance was enough to drag it into equal 3rd on the MAFL Tipster table on 99 from 152 (65%). Ahead of it, in 1st, is Easily Impressed II on 101 (66%) and Short-Term Memory II in 2nd on 100 (66%).

BKB managed just 4 for the weekend, taking it to 95 (62.5%) for the season and relegating it to equal 3rd-last position. Over the past four rounds, favourite-tipping has yielded just 15.5 winners from 32 games, some four tips worse than what could have been achieved by someone merely consulting the most recent football ladder pre-round and then selecting the team higher on it.

On average, MAFL Tipsters scored 4.5 from 8 for the week.

Positions on the MARS Rating table were once again highly-tradeable commodities this weekend, as 10 of the 16 teams decided they didn't like the spot they already had. Five teams climbed and five fell. Collingwood and Carlton climbed most, ascending two places each, Collingwood into 1st and Carlton into 5th.

Essendon was the only team to fall multiple places. They dropped two spots into 13th.

There are now eight teams rated above 1,000 on MARS Ratings and these are the same eight teams that occupy the top eight spots on the competition ladder, though in a different order. The Top 3 teams on MARS Ratings, which were separated by only about 4 Rating Points before the round, are now separated by just 1.5 points.

All Margin Tippers saw their Mean Absolute Prediction Error rise this week, which left the top 3 places unchanged and occupied by BKB, LAMP and ELO. LAMP, however, suffered a smaller MAPE increase than BKB and so is now only 0.22 points per game behind.

The Median Absolute Prediction Errors for Chi, ELO and LAMP all rose by 0.5 points, while BKB's and HAMP's remained unchanged, which allowed HAMP to join ELO in equal 2nd on 27 points, behind LAMP on 26.

HELP this week recorded its third successive 5 from 8 performance and is now only one tip behind the result you could rightfully have expected had you tossed a coin each week to determine your line bets. HELP's Probability Scores are all still manifestly sub-naive.

In contrast, SSM continues to tantalise. It correctly tipped 6 of the 8 line results this week and now has a 56.6% season-long record. (Last week I think I might have quoted SSM's 2006-2010 record when I gave this statistic as 54.5%).

The Bookie Probability Model's lone wager for the round, which was 2.4% on the Swans, was also successful.