The win probabilities for UFC 229’s seven qualifying matchups are in. Here are the estimated odds for each bout where both fighters have at least four fully-documented prior fights and aren’t heavyweights. For statistical overload on the distance, clinch, and ground alternative stats behind Khabib-McGregor, Ferguson-Pettis, and Waterson-Herrig, see Tuesday’s piece.
Khabib Nurmagomedov (70.5%) over Conor Mcgregor (29.5%)
Sergio Pettis (54.3%) over Jussier Da Silva (45.7%)
There’s no human element to these probabilities and picks (other than the original training and testing). They’re 100% from a machine crunching fight stats. Sometimes I agree with them and sometimes I think they’re crazy. Sometimes I’ve been right, other times pleasantly surprised. To date, the model has a 60.0% success rate on picks and 41.0% success on bets. Meanwhile, the money line favorites have won at a 65.9% rate.
In a future more detailed breakdown, I plan on comparing it to other media picks. Ben Fowlkes and Jordan Breen each got off to a hot start, but I haven’t tracked most media’s picks for the last 8-9 months since they can always be searched later.
I pissed away $400 on a human error and the model’s currently on a 6-of-7 bet losing stretch. No fun, but we’re looking at:
Current Bankroll: $9,338.67
No-Human-Error Bankroll: $9,736.04
The model has $93.39 on Gray Maynard at +195 (as of 2:30pm PT).
Enjoy the glorious fights!
Note: This is an experiment and entertainment. Do not bet on the fights using these numbers. Taking sensible gambles with an edge over time is similar to investing. But if I’ve made a mistake somewhere, those same gambles without an edge become sucker bets. Let me be the possible sucker. You’ve been warned.