About

I set out to develop a model that needed the barest of inputs: just the two teams involved and the final score. That way I’d be able to predict Le Crunch and the Bledisloe Cup as well as I could a match in URBA or the PWR, and not be dependent on data collection or media coverage of individual matches. I’ve acomplished that with my club model, then developed a player-based model that only requires teamsheets to be added but allows for player and club rankings. Now I have predictions being made for every professional match that I can find data for, and can dig into the best ways to share out my data and visualize what I’ve developed.

So over time, I’ll likely be squeezing what I can out of these frameworks and leveraging them to develop some things like in-match win probabilities, player history views, or rating games by interest. Whatever sounds most interesting to me, really - but feel free to toss me some ideas if you’ve got them.

Some Non-Rugby Things

In doing all this, I’ve also made a pretty flexible framework for multiplayer competitions, which can be applied to some other sports. I have some experimental applications to other sports I watch, and those may be added to this site over time.

This is entirely separate from my actual paying job, however, so don’t expect any firm roadmaps. If you’re invested in this continuing or expanding, let me know. If you’re instead looking for some predictive help for your problems, reach out here for some consulting. I ramble a lot less in that work.

FAQs

How much AI?

Inline completions with a local model, and some of the background css visuals on this site because I’m not a web dev.