Matter of Stats

View Original

The MoS Tipsters, Predictors and Funds for 2020

This is, I think, by far the furthest into a calendar year that I’ve posted about my plans for the upcoming men’s AFL season, though that’s not because I haven’t been making significant changes in preparation for it.

As some of you who subscribe to the e-mail will know, both MoSSBODS and MoSHBODS have undergone some off-season renovations that will hopefully be improvements, and as some who follow me on Twitter will know, I’ve decided to retire all three of the ChiPS-based models this season.

Here is a list of all the changes:

  • MoSHBODS: Now called MoSH2020 and identical to MoSHBODS in philosophy, but a little different in terms of some of the mechanics. Have a look at the post linked above for details.

  • MoSSBODS: Now called MoSS2020 and identical to MoSSBODS in philosophy, but also a little different in terms of some of the mechanics. See linked post.

  • C_Marg and C_Prob: Retired. No replacements, although I did build margin and probability predictors that used bookmaker, MoSH2020, MoSS2020, MARS, and team result data as inputs, but they proved to be no better than MoSH2020 alone, so they’ll not get a start in 2020.

  • ENS_Linear: Newly optimised based on the most-recent 10 years worth of data, as is tradition.

  • MoSHPlay: Will be a combination of MoSH2020 and the player-based SuperCoach forecasts (more about which you can find in this post from last year). The formulae to combine the two have been re-optimised, and are:

    • Expected Home Margin = -1.94 + 0.79 x MoSH2020 Expected Margin + 1.97 x Mean SC Forecast Difference

    • Expected Total = 101.2 + 0.57 x MoSH2020 Expected Home Score + 0.86 x MoSH2020 Expected Away Score + 0.08 x Home Mean SC Forecast - 0.80 x Away Mean SC Forecast

    • Prob(Home Win) = 1/1+exp(-(-0.021 + 0.033 x MoSH2020 Expected Margin + 0.137 x Mean SC Forecast Difference))

  • All of these other tipsters, predictors and models are as per last season (including the MARS Team Rating System). You can find out more about them in this blog from 2016 and, if you're new, more about how it all works here on MoS in this post from 2015, although many of the statistical models discussed there are no longer in use.

So, in total, there will be nine traditional Head-to-Head Tipsters, 10 Margin Predictors, and six Head-to-Head Probability Predictors in 2020, as listed in the table below.

MOS FUNDS

MoS will again be wagering in the Head-to-Head, Line and Over/Under markets this season, albeit with different portfolio weights for the Funds.

HEAD-TO-HEAD FUND (WEIGHTING 30%)

The Head-to-Head Fund grew by just over 29% across the 2019 season after recording a +14.8% ROI on a 2.0 turn, and was pleasingly profitable across all parts of the season, although relatively quiet from Round 21 onwards. This was a much-improved performance compared to 2018.

MoSH2020 will inform this Fund’s wagering this year, and we’ll be slightly up-weighting the Fund in the Portfolio but continuing with the rules we used last year about when and how much to wager.

  • Wagers will only be made on home teams and when the estimated edge is over 5% (ie Price x Estimated Probability > 105%).

  • A fixed-return staking strategy will be used such that, should a wager be successful, the Fund will increase in value by 2% of its original size.

Achieving the second outcome requires that wagers be sized as follows:

Wager Size (as % of original funds) = 1/(50*(Price-1))

As I said last year, the move away from Kelly-staking is an acknowledgement that, absent the services of a very well-calibrated algorithm, accurately estimating your edge is impossible, and assuming that you can estimate it accurately is especially fraught for short-priced favourites.

For example, if you’ve estimated that a $1.30 favourite has an 85% chance of victory, then a full Kelly stake would have you betting (85% x 1.3 - 1)/(1.3 - 1), or 35% of your bankroll. If that team’s actual chances were 80%, then the correct Kelly stake would be (80% x 1.3 - 1)/(1.3 - 1) or just 13.3% of your bankroll, which is less than 40% of the wager you’d actually make.

Fixed-return staking is broadly agnostic about the magnitude of the estimated edge, the exception being that we’re only wagering at all when we estimate the edge exceeds the threshold value of 5%. Once we’re over that threshold, however, the bet size is fixed so that, for example, the wager where the estimated edge is 6% is no different to that where it’s estimated to be 20%.

LINE FUND (WEIGHTING 60%)

Line wagering has been consistently profitable here on MoS, returning profits in 2008, 2010, 2011, 2013, 2014, 2016, 2017, 2018 and 2019 (and only small losses or break even results in 2007, 2009 and 2012). A 20% loss in 2015 is the only significantly bad result across the 13 seasons from 2007 to 2019.

Last year, line wagering was informed by MoSSBODS, and saw profits in all but nine rounds. The season finished with the Line Fund producing about a 34% profit from a 17.9% ROI on a 1.9 turn. Of the 92 bets placed, 53 (58%) were winners.

This year, the Line Fund will rely on MoSS2020, and will still be permitted to wager on home and on away teams. Also as per last year, it will place a line bet on a team proportional to the size of its measured 'advantage', only when the handicap set by the TAB or BetEasy bookmaker is assessed by MoSS2020 as being in error by more than 8 points. History suggests that MoS Funds are far better at estimating their edge in the line market than in the head-to-head market, and prices are typically around $2, so the issue with short-priced favourites and miscalibration does not apply.

Bet size, as a percentage of initial Funds, will again be determined as:

Bet Size = (Assessed Margin + Handicap Offered - 8)/300
provided Assessed Margin + Handicap Offered > 8

So, for example, if the Home team is giving 12.5 start and MoSSBODS assesses them as winning by 33 points, the bet would be (33 - 8 - 12.5)/300 = 4.2% of initial Funds.

Instead, if the Away team is receiving 34.5 start and MoSSBODS assesses them as losing by only 12 points, the bet would be (34.5 - 8 - 12)/300 = 4.8% of initial Funds.

As a response to its consistent profitability, the Line Fund will be up-weighted this year to represent 60% of the Overall Portfolio.

OVER/UNDER FUND (10%)

Were there parent-teacher nights for MoS Funds, the Over/Under Fund’s maths teacher would be anxiously watching the classroom door, hoping that Fund’s parents decided not to show up.

The Fund disappointed again last year (albeit less thoroughly than the year before) despite being up by almost 17% just six rounds into the season. Overall, it collected on only 40 of 78 wagers and finished down by just over 5% on the season from a -3.5% ROI on a 1.6 turn. And that, despite for the first time having some awareness of the forecast weather.

As a consequence, the Fund will be significantly down-weighted in the overall Portfolio to just 10%.

MoSSBODS will again provide wagering advice for the Fund and will again require a 6 point minimum overlay before wagering. All wagers will again be a flat 2% of the Fund and no unders bets will be made if there is any forecast of rain.

All three Funds will wager in whichever of the TAB or Easybet markets are offering the most attractive prices and are accepting my bets, and will be placed:

  • For head-to-head and line bets: as soon as possible after the Line markets are posted on both TAB and Easybet

  • For over/under bets: as soon as possible after the Totals markets are posted on both TAB and Easybet

BLOG SCHEDULE

The following is the rough schedule I plan to follow this season (client work and life permitting):

Monday or Tuesday night: blog with week’s head-to-head, margin and head-to-head probability forecasts, plus Head-to-Head and Line wagers assuming availability of markets.

Tuesday or Wednesday night: blog with latest team rating data

Wednesday or Thursday night: blog with week’s over/under wagers

Thursday night (and otherwise, as required due to team announcements): blog with week’s player-based forecasts

Sunday night (except in rounds with Monday night games): blog with results for the round, plus team dashboard data

Since this year I’ve been coerced into projecting the remainder of the season before it’s even begun (which, I’m told, given my previous assertions, has had the Devil nervously eyeing the thermostat), there will also be weekly updates on those projections somewhere during the course of the week.

Finally, I plan also to blog occasionally about any interesting statistical analyses that I get the time to conduct.

It’s going to be another very busy year. Hope you can stay for the ride.

(And, if you enjoy what’s here, consider clicking on that Donate button and buying me a coffee. I don’t expect to get rich from MoS, but any encouragement is much appreciated. Thank you to everyone who has already donated, commented, or sent me an e-mail. I do read them all and respond as soon as I can.)