A data-driven approach to understanding the features of the AFL Supercoach pricing mechanism — The AFL Supercoach pricing mechanism is a much simpler implementation of the one used for AFL Fantasy. By comparison, there is also much more written up on the methodology. Hence, this article has been written for the purposes of completeness to my body of work on AFL statistics. In the…

A framework for tracking and attributing the components of player effectiveness — In our original paper, we demonstrated that a baseline model using player age, draft pick and position can be used to explain a large proportion of each of the following components — points per minute, time on ground and percentage of season played — across the AFL player cohort. Lifecycle of an AFL player’s career Stages of an AFL player’s career and a first model for assessing player effectiveness across multiple seasonstowardsdatascience.com

Stages of an AFL player’s career and a first model for assessing player effectiveness across multiple seasons — In this article we explore the lifecycle of an AFL player’s career and try to understand the interplay of playing position, talent and experience using an expectations based framework, and propose our first model for estimating player value. Given that the ultimate purpose is to select players who are most…

Where’s Wally … statistics which tell the story of player roles — A casual observation from previous research was that some player statistics contained sufficient information to define player positions in the absence of video footage and/or actual x-y coordinates of ball action. Classifying AFL Team Stats Identifying meaningful structures in AFL team stats using cluster analysismedium.com Our starting point is the following charts which shows the relative frequency of each variable grouped by player position…

A look at AFL players in the context of their own teams — This article uses data visualisations to examine player impact and importance within their own teams as a way of understanding team construction, with some takeaways for AFL fantasy. Data The publicly available statistics were scraped from the individual pages for each match from Footywire for the 2019 season. The raw dataset…

Using Principal Components Analysis to explore the link between player position and fantasy scores — In our prior analysis on classification of AFL team statistics we observed that in principal components space, the first two components of PCA suggested that the data can be organised by (1) ball ownership and (2) ball location relative to the midfield. In this article we drill down the dataset…

Understanding how initial player prices are determined using classification and regression algorithms — One of the problems in early preparation of my AFL fantasy team for the upcoming season is that player fantasy prices are not available on the Footywire website until season commencement. In investigating the methodology for the pricing calculation, we find that the pricing specifications are slightly incomplete as they…

Introducing Wilma, an Elo style model for rating AFL team strength and quality — In this article we introduce Wilma, our first rating system for AFL team strength and quality. Wilma is an Elo style model which compares team strength and quality over time. Wilma’s record in predicting match winners is an accuracy of 68.2% over the entire AFL history and 65.8% …

Exploratory data analysis on conversion rates in AFL matches — Following on from my last analysis on clustering of team stats, it becomes more apparent that a model for match outcomes needs to consider both the generation of scoring opportunities in the midfield and the execution of scoring opportunities in the goal square. In this article I explore the latter…