What's Easier - Predicting the Home or the Away Team Score?

/
Consider the following scenario. You're offered a bet in which you can choose to predict the final score of the Home or of the Away team and your adversary is then required to predict the final score of the other team.
Read More

Setting an Initial Rating for GWS

/
Last season I set Gold Coast's initial MARS Rating to the all-team average of 1,000 and they reeled off 70 point or greater losses in each of their first three outings, making a mockery of that Rating. Keen to avoid repeating the mistake with GWS this year, I've been mulling over my analytic options.
Read More

A First Look At Surprisals for 2011

/
We first discussed surprisals back in 2009 (if you perform a site search using the term "surprisals" you'll be linked to a couple of PDFs as well as to a handful of blog posts on the topic) as a method for quantifying the surprise associated with the outcome of a football game.
Read More

Projecting the Favourite's Final Margin

/
In a couple of earlier blogs I created binary logit models to predict the probability that the favourite would win given a specified lead at a quarter break and the bookmaker's assessed pre-game probability for the favourite. These models allow you to determine what a fair in-running price would be for the favourite. You might instead want to know what the favourite's projected victory margin is given the same input data, so in this blog I'll be providing some simple linear regressions that provide this information.
Read More

An Empirical Review of the Favourite In-Running Model

/
In the previous blog we reviewed a series of binary logits that modelled a favourite's probability of victory given its pre-game bookmaker-assessed head-to-head probability and its lead at the end of a particular quarter. There I provided just a single indication of the quality of those models: the accuracy with which they correctly predicted the final result of the game. That's a crude and very broad measure. In this blog we'll take a closer look at the empirical model fits to investigate their performance in games with different leads and probabilities.
Read More

Hanging Onto a Favourite: Assessing a Favourite's In-Running Chances of Victory

/
Over the weekend I was paying particular attention to the in-running odds being offered on various games and remain convinced that punters overestimate the probability of the favourite ultimately winning, especially when the favourite trails.
Read More

Line Fund Profitability and Probability Scores

/
Over on the Simulations blog as part of a more general investigation into the dynamics of the contest between punter and bookmaker in head-to-head wagering I've looked at the relationship between the probability score attained by the Head-to-Head Fund in each season and its profitability. What I found, among other things, was that the Fund's profitability was related not to the absolute probability score of the Fund algorithm, but to its probability score relative to the bookmaker's.
Read More

Predicting a Team's Winning Percentage for the Season

/
In recent blogs where I've been posting about a win production function the goal has been to fit a team's season-long winning percentage as a function of its scoring statistics for that same season. What if, instead, our goal was to predict a team's winning percentage at the start of a season, using only scoring statistics from previous seasons?
Read More

Underachieving and Overachieving Teams

/
A couple of blogs back I described some win production functions, which relate a team's winning percentage in the home-and-away season to characteristics of its scoring during that season, in particular to its rate of scoring shot production and its conversion of those scoring shots relative to its opponents'.
Read More

Applying the Win Production Functions to 2009 to 2011

/
In the previous blog I came up with win production functions for the AFL - ways of estimating a team's winning percentage on the basis of the difference between the scoring shots it produces and those it allows its opponents to create, and the difference between the rate at which it converts those scoring shots and the rate at which its opponents convert them.
Read More

Win Production Functions for AFL Teams - 1897 to 2010

/
Right now I'm reading Wayne L Winston's Mathletics, a book about the use of fairly simple mathematics and sports statistics to gain insights into the results of American sports. Inspired by this book, in particular by a piece on Pythagorean Expectation which relates the season-long winning percentage of a baseball team to the total runs that it's scored and allowed, I wondered if an AFL team's win percentage could be similarly predicted by a handful of summary statistics about its own and its opponents' scoring.
Read More

The Calibration of the Head-to-Head Fund Algorithm

/
In the previous blog we considered the logarithmic probability score on ProPred, WinPred and the TAB bookie and found that the TAB bookie was the best calibrated of the three and that relative tipping performance was somewhat unrelated to relative probability scores. For the Head-to-Head Fund, whose job in life is to make money, the key question is to what extent do its probability scores relative to the TAB bookie's shed light on its money-making prowess.
Read More

Assessing ProPred's, WinPred's and the Bookie's Probability Forecasts

/
Almost 12 months ago, in this blog, I introduced the topic of probability scoring as a basis on which to assess the forecasting performance of a probabilistic tipster. Unfortunately, I used it for the remainder of last season as a means of assessing the ill-fated HELP algorithm, which didn't so much need a probability score to measure its awfullness as it did a stenchometer. As a consequence I think I'd mentally tainted the measure, but it deserves another run with another algorithm.
Read More

Home Team Wagering: Rumours of Its Death Have Been Greatly Exaggerated

/
I should probably have noticed this sooner, but last year was quite a profitable year for blindly wagering on Home Teams. A gambler who level-staked the AFL Designated Home Team in every game in the head-to-head and in the line market would have recorded an 8.4% ROI on his or her head-to-head wagers and a 4.1% ROI on his or her line wagers.
Read More

Ensemble Models for Predicting Binary Events

/
I've been following the development of prediction markets with considerable interest over the past few years. These are markets in which the opinions of many engaged experts are combined, the notion being that their combined opinion will be a better predictor of a future outcome than the opinion of any one of them. It's a notion that has proved right on many occasions.
Read More

Can We Do Better Than The Binary Logit?

/
To say that there's a 'bit in this blog' is like declaring the 100 year war 'a bit of a skirmish'.

I'll start by broadly explaining what I've done. In a previous blog I constructed 12 models, each attempting to predict the winner of an AFL game. The 12 models varied in two ways, firstly in terms of how the winning team was described ...
Read More