News

Update After a discussion with Chris from wolftickets.ai, I did some more feature engineering and feature selection. The most important ones were an impact stat, redoing the ratios, and lowering the amount of features to about 30, down from 80-100. Divide by zero Ratios (fighter1_stat / fighter2_stat) have always been important to the algorithm, they’re […]

After 6 months of work, I’m finally more or less done with version 3. Currently it’s testing at 64% accuracy, .65 logloss on the latest 10% of UFC fights that the model has never seen. Updates Custom Elo The Elo scoring system was overhauled. It now has 17 custom scoring weights that affect the Elo

For version 1.4 I’ve decided to double down on making less predictions but more accurately. I have eliminated heavyweight fighters who, statistically, fight very differently than every other weightclass. They’re an outlier weightclass just like women’s MMA is. I have retuned the hyperparameters using Optuna, and I have added a feature incorporating title fight losses

Last event went 1/4 in best predictions and the one win was essentially guaranteed with bookies setting the odds at -1000. This is because A) I’m not doing unit testing, and B) I introduced (and reintroduced) multiple bugs into the model via the latest release. It is painful to do hundreds of hours of coding

The model now includes a new engineered stat which measures the highest and lowest values in each stat column and also compared their current stat to their peak and valley. This almost quadruples the model’s total stats. Accuracy increased from 68.8% to 71.1%. Return On Investment has increased from 21% to 28% for the last

I had to take down the predictor.mma-ai.net web application that let you check the odds of any fighter based on the algorithm because it costs me $150 for an EC2 instance with enough memory, CPU, and space to make the predictions. This makes me sad because it was the first Flask app I’d ever developed