UFC 9: Motor City Madness: Predictions & Analysis
UFC 9: Motor City Madness lands on Friday, May 17, 1996 in Detroit, Michigan, USA with 7 bouts on the card. Below is our fight-by-fight breakdown, combining Elo ratings, rolling statistical trends, style matchup data, and betting market context into a pick for every bout.
Quick Picks
| Matchup | Pick | Confidence | Prob |
|---|---|---|---|
| Dan Severn vs Ken ShamrockOpen Weight | Dan Severn | Lean | 59% |
| Don Frye vs Amaury BitettiOpen Weight | Don Frye | Strong | 86% |
| Mark Hall vs Koji KitaoOpen Weight | Mark Hall | Lean | 64% |
| Mark Schultz vs Gary GoodridgeOpen Weight | Gary Goodridge | Strong | 87% |
| Rafael Carino vs Matt AndersenOpen Weight | Rafael Carino | Lean | 65% |
| Cal Worsham vs Zane FrazierOpen Weight | Cal Worsham | Confident | 75% |
| Steve Nelmark vs Tai BowdenOpen Weight | Steve Nelmark | Confident | 72% |
Like these picks? Bet on DraftKings
Place your bets on the fights above at DraftKings Sportsbook
Bet Now on DraftKingsFight-by-Fight Breakdown
Dan Severn vs Ken Shamrock
The Open Weight matchup features Dan Severn (9-4) taking on Ken Shamrock (6-5).
There's a real Elo separation here: Severn at 1355 versus Shamrock at 1231. That 123-point gap typically reflects a meaningful difference in recent quality of competition and results.
Both fighters land in our "Submission Artist" archetype — ground specialists who hunt for finishes off their back or from top position. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Severn throws significantly more leather — a 1.1 sig. strike per minute gap. Shamrock is far more active with takedowns, averaging 0.6 more per 15 minutes. Shamrock has tighter striking defense, making opponents miss more often.
The Pick: Dan Severn over Ken Shamrock. The model gives Severn a slight nod at 59% — this could easily go either way.
Don Frye vs Amaury Bitetti
The Open Weight matchup features Don Frye (9-1) taking on Amaury Bitetti (1-1).
Frye is rated at 1461 — 507 points above Bitetti's 955. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Frye throws significantly more leather — a 6.3 sig. strike per minute gap. Frye is far more active with takedowns, averaging 4.7 more per 15 minutes. Bitetti has tighter striking defense, making opponents miss more often.
The Pick: Don Frye over Amaury Bitetti. The model is firm on this one: Frye at 86%.
Mark Hall vs Koji Kitao
The Open Weight matchup features Mark Hall (4-3) taking on Koji Kitao (0-1).
Hall is rated at 1119 — 204 points above Kitao's 915. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Hall throws significantly more leather — a 0.4 sig. strike per minute gap. Kitao is far more active with takedowns, averaging 0.0 more per 15 minutes. Kitao has tighter striking defense, making opponents miss more often.
The Pick: Mark Hall over Koji Kitao. The model gives Hall a slight nod at 64% — this could easily go either way.
Mark Schultz vs Gary Goodridge
The Open Weight matchup features Mark Schultz (1-0) taking on Gary Goodridge (4-4).
There's a real Elo separation here: Schultz at 1304 versus Goodridge at 1198. That 106-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Goodridge throws significantly more leather — a 1.6 sig. strike per minute gap. Goodridge is far more active with takedowns, averaging 5.7 more per 15 minutes. Schultz has tighter striking defense, making opponents miss more often.
The Pick: Gary Goodridge over Mark Schultz. The model is firm on this one: Goodridge at 87%.
Rafael Carino vs Matt Andersen
The Open Weight matchup features Rafael Carino (1-0) taking on Matt Andersen (0-1).
Carino is rated at 1191 — 382 points above Andersen's 809. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Andersen throws significantly more leather — a 0.0 sig. strike per minute gap. Andersen is far more active with takedowns, averaging 0.0 more per 15 minutes. Andersen has tighter striking defense, making opponents miss more often.
The Pick: Rafael Carino over Matt Andersen. The model gives Carino a slight nod at 65% — this could easily go either way.
Cal Worsham vs Zane Frazier
The Open Weight matchup features Cal Worsham (1-2) taking on Zane Frazier (0-1).
Worsham is rated at 962 — 289 points above Frazier's 673. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Worsham throws significantly more leather — a 8.7 sig. strike per minute gap. Frazier is far more active with takedowns, averaging 0.0 more per 15 minutes. Frazier has tighter striking defense, making opponents miss more often.
The Pick: Cal Worsham over Zane Frazier. We're leaning Worsham here at 75%, a solid but not overwhelming edge.
Steve Nelmark vs Tai Bowden
The Open Weight matchup features Steve Nelmark (2-1) taking on Tai Bowden (1-1).
There's a real Elo separation here: Bowden at 1096 versus Nelmark at 1002. That 93-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Bowden throws significantly more leather — a 0.0 sig. strike per minute gap. Bowden is far more active with takedowns, averaging 0.0 more per 15 minutes. Bowden has tighter striking defense, making opponents miss more often.
The Pick: Steve Nelmark over Tai Bowden. We're leaning Nelmark here at 72%, a solid but not overwhelming edge.
Methodology
Predictions are generated by our ensemble model combining LightGBM (65%) and CatBoost (35%), trained on every UFC fight since 1994. The model uses 23 features including Elo ratings, rolling 5-fight statistical averages, style matchup history, physical attributes, and market odds when available.
On our held-out test set (402 fights from January-September 2023), the model achieves 63.4% accuracy with a log-loss of 0.626. High-confidence picks (>75% probability) hit at 82.7%. For full model transparency, visit our Model page.