Oddacious


Collecting my notes on sports analytics and other assorted topics

Hockey Hall of Fame model update 2022

Looking at the past and future of the hall

It has been three years since I last checked in with my Hockey Hall of Fame (HHOF) model. Let's see how it did recently and which active players are moving up the ranks.

NBA win predictions 2019-2020

Adapting my NBA season model for 2019-20

Per my annual tradition, here are NBA playoff odds generated using the model that I shared last year, the year before, and the year before that.

Update on the Hockey Hall of Fame model and its predictions

Hockey Hall of Fame 2019 review and 2020 forecast

Who made it in, who will make it in next year, and how borderline are some of our favourite not-yet-eligible players?

2018-19 NBA predictions retrospective

Looking at how my NBA playoff model performed in 2018-19

I'm not here to gloat. Or at least, not about the Raptors. I'm here to gloat about my predictions.

Proper scoring rules

How should we evaluate probabilistic forecasts?

I love how this literature, and our entire understanding of probability, has either been about predicting rainfall of profiting through gambling.

NBA win predictions 2018-2019

Adapting my NBA season model for 2018-19

A lot of these teams are really dragged down by having a few weak players, especially if they're expected to play significant minutes.

Update on the Hockey Hall of Fame model and predictions

The Hockey Hall of Fame in 2018, 2019, and beyond

Next year could go in many directions, since there are no sure-fire NHL candidates. There's no Martin Brodeur or Teemu Selanne. The most accomplished player might not be an NHLer, since it looks like Hayley Wickenheiser is eligible. This gives the committee a lot of room to reconsider players it overlooked in the past.

NBA win predictions 2017-2018

Adapting my NBA season model for 2017-18

Some of these teams will be much better than expected, and some will be much worse, but right now we don't know which.

Aiming for generalization with Hockey Hall of Fame models

On complexity and overfit in hockey models

We can fit the data perfectly, but we shouldn’t. This is what’s known as the bias-variance trade-off. The more precise we try to be in fitting the data at hand, the more likely we memorize effects that are due to random variation in the training data that do not generalize to other datasets.

5 players who should be in the NHL's 100 greatest

5 additions and subtractions to NHL's 100 greatest list

I love lists, and I love arguing, so here are five players who should be on the top 100, and who they could take off.