BCDC Data Scientist Previews UFC Fight Night: Everything You Need to Know
BCDC Data Scientist, Brandon Bergstrom, is 24-10 with over 14.3U on these 50/50 fight picks. This weekend’s fights are great to look at from a data perspective since both matchups are exciting well-known fighters.
Nick Maximov vs Jacob Malkoun
We project this to be a striking fight. This is a clear advantage for Nick Maximov who is much more of a volume striker. Maximov being a volume striker will also play a key role if the fight goes the distance. Most of the time, the volume striker wins the fight unless something shocking like a knockdown happens.
Nick has the experience and stats to show why he should win this fight. He has the control time stat and volume striking in his favor. Check out our Search page to review these fighters more closely.
Fighters with a reach of 76 inches, such as Nick Maximov, are 1-4 in the last 5 fights at Middleweight. This is a quite alarming stat for Middleweights and should make us want to do more testing on who might win this fight without just guessing.
Running our statistical simulation model we see this though…
Fights simulated: 1000
Wins for Nick Maximov 48
Wins for Jacob Malkoun 952
It is quite alarming to see this massive of a difference, especially since Nick has the better offensive numbers. However, he has much worse defensive numbers and, in that case, Jacob Malkoun is able to defend and use his strikes effectively to win the fights in the simulation at almost perfect rate.
In seeing this final output, I will be rolling with Jacob Malkoun to win this fight and get the underdog win.
Cub Swanson vs Jonathan Martinez
This fight is the old savvy veteran vs. the young up and comer. Taking a look at the dominance score calculated by BCDC, we can see Martinez has done much better than Swanson recently which is important to see.
Calculating Dominance Score
Example KO win = 5 Points
Example Split Decision Win = 1
Example U Decision Win = 2.78
Example U Decision Loss = -2.78
Not all wins are created equal. Historical data is how we create the point system for different outcomes.
Cub Swanson is above .500 for winning against similar volume fighters to Jonathan Martinez. Cub Swanson is 8-6 against fighters with 10 or more for Total Strikes Attempts 1 min.
Here are some ridiculous stats on the opposite side of this fight.
Jonathan Martinez is 2-0 against fighters with 8 or more for Sig. Str. Head Attempts 1 min.
Jonathan Martinez is 3-0 against fighters with 11 or more for Total Strikes Attempts 1 min.
However, rolling out our statistical simulation, we see the following:
Fights simulated: 1000
Wins for Cub Swanson 750
Wins for Jonathan Martinez 250
The simulation shows a huge underdog win by Cub Swanson. This is intriguing and the data supports Cub in a head-to-head matchup… but preview stats favor Martinez, so let’s do another simulation model. We will use our Bayesian Simulation model to help us gauge who will win. The ore information we have, the better for us.
Using Bayesian Simulation and not machine learning models, beforethecagedoorcloses is 65% sure that Jonathan Martinez is the better fighter with a risk of being wrong at 12%.
This fight is a really close call and, using our statistical models, it’s clear why it’s a tough fight to predict. The fighters will definitely not win by finish. Historically, the fight has a 54.8% chance it goes the entire 3 rounds. Odds are -135 for this fight to go the distance. We are predicting this fight to go the distance and be a 29-28 type of win.
I am rolling with Cub Swanson, and it’s because he is cheaper, the fight will go down to experience, and he seems to have the will to win. Cub Swanson is fighting for more than just a win this weekend. He is fighting to stay in the company. I believe he will squeeze out a W. Martinez struggles once the fight gets going in round 3. Cub is cheap and models are projecting him to win this fight. Cub Swanson is +175 with statistical simulation backing him up.
