Skills

R

Python

Matlab

Visualisation

Machine Learning

Optimisation

Hello there, it’s been a while! Today is a short retrospective of the underwhelming 2019 Squiggle tipping competition performance. We’ll be covering what went wrong, some key learnings and how to improve for next year. It’s safe to say that AFLgains squiggle performance was not up to standard. Overall, the model managed 130 correct tips at an accuracy of 62.3% (3rd to last). We also came 2nd to last in bits, only managing 12.

CONTINUE READING

Now that the bye-rounds are done and dusted, I thought it would be a good idea to have a look at the effect that bye-rounds have historically had on team performance. Some people believe that teams coming off the bye tend to have a lower chance of winning than usual. Perhaps the bye breaks the in-season “momentum”, or that players lose concentration after their extended break. But as human beings, we have a strong tendency to confirmation bias and weight recent information more heavily than we should.

CONTINUE READING

Bar chart races have become very popular in recent times, to the point where they are viral. As such, I thought I would set out to create my own bar chart race and publish it on the internet.

CONTINUE READING

I used mathematics to create an alternative 2018 fixture, one that is predicted to increase total annual attendance by ~300K, while still sticking within the fixturing rules. In the article discuss how I created the solution, the final results and the impact of certain fixturing rules. Amongst other things, the study demonstrates that optimal number of Friday night matches for Carlton is indeed 5, and that the AFL foregoes ~100k per year to ensure league parity.

CONTINUE READING

I made a machine learning algorithm to predict AFL matches before they started. When I simulated my results on 2017 matches and used it for betting, I managed to get a net positive return on my investments.

CONTINUE READING

Contact