UFC Fight Night: Shields vs Ellenberger: Predictions & Analysis
UFC Fight Night: Shields vs Ellenberger lands on Saturday, September 17, 2011 in New Orleans, Louisiana, USA with 12 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 |
|---|---|---|---|
| Jake Ellenberger vs Jake ShieldsWelterweight | Jake Ellenberger | Strong | 77% |
| Court McGee vs Dongi YangMiddleweight | Court McGee | Confident | 68% |
| Erik Koch vs Jonathan BrookinsFeatherweight | Jonathan Brookins | Lean | 57% |
| Alan Belcher vs Jason MacDonaldMiddleweight | Alan Belcher | Lean | 63% |
| Vagner Rocha vs Cody McKenzieLightweight | Cody McKenzie | Lean | 64% |
| Evan Dunham vs Shamar BaileyLightweight | Shamar Bailey | Toss-up | 52% |
| Lance Benoist vs Matthew RiddleWelterweight | Matthew Riddle | Lean | 57% |
| Ken Stone vs Donny WalkerBantamweight | Ken Stone | Lean | 55% |
| Seth Baczynski vs Clay HarvisonWelterweight | Seth Baczynski | Lean | 56% |
| TJ Waldburger vs Mike StumpfWelterweight | TJ Waldburger | Confident | 67% |
| Robert Peralta vs Mike LulloFeatherweight | Robert Peralta | Lean | 62% |
| Justin Edwards vs Jorge LopezWelterweight | Justin Edwards | Lean | 55% |
Fight-by-Fight Breakdown
Jake Ellenberger vs Jake Shields
The Welterweight matchup features Jake Ellenberger (10-10) taking on Jake Shields (4-2). There's a 3-inch height gap favoring Shields.
Shields is rated at 1232 — 385 points above Ellenberger's 847. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Ellenberger's submission artist game against Shields's striker approach. Ellenberger is most dangerous on the ground, constantly threatening chokes and joint locks, while Shields brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Shields throws significantly more leather — a 0.3 sig. strike per minute gap. Ellenberger is far more active with takedowns, averaging 2.7 more per 15 minutes. Ellenberger has tighter striking defense, making opponents miss more often.
The Pick: Jake Ellenberger over Jake Shields. The model is firm on this one: Ellenberger at 77%.
Court McGee vs Dongi Yang
The Middleweight matchup features Court McGee (11-12) taking on Dongi Yang (1-3).
The Elo gap here is razor-thin — McGee at 1037, Yang at 1066. On paper, this is as close to a coin flip as it gets.
A few statistical edges stand out. Yang throws significantly more leather — a 0.3 sig. strike per minute gap. McGee is far more active with takedowns, averaging 2.8 more per 15 minutes. McGee has tighter striking defense, making opponents miss more often.
The Pick: Court McGee over Dongi Yang. We're leaning McGee here at 68%, a solid but not overwhelming edge.
Erik Koch vs Jonathan Brookins
The Featherweight matchup features Erik Koch (4-5) taking on Jonathan Brookins (2-2). Brookins is the bigger frame at 6'0" with a 3-inch reach advantage.
Koch carries a modest Elo edge (1017 to 984), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
A few statistical edges stand out. Brookins throws significantly more leather — a 0.6 sig. strike per minute gap. Brookins is far more active with takedowns, averaging 3.0 more per 15 minutes. Koch has tighter striking defense, making opponents miss more often.
The Pick: Jonathan Brookins over Erik Koch. The model gives Brookins a slight nod at 57% — this could easily go either way.
Alan Belcher vs Jason MacDonald
The Middleweight matchup features Alan Belcher (9-5) taking on Jason MacDonald (6-7). MacDonald will look to use a 5-inch reach edge to control distance.
Belcher is rated at 1293 — 462 points above MacDonald's 831. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Belcher's knockout artist game against MacDonald's wrestler approach. Belcher is patient on the feet, timing counters and loading up when he sees openings, while MacDonald looks to close distance and put the fight on the mat. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Belcher throws significantly more leather — a 2.2 sig. strike per minute gap. MacDonald is far more active with takedowns, averaging 2.6 more per 15 minutes. Belcher has tighter striking defense, making opponents miss more often.
The Pick: Alan Belcher over Jason MacDonald. The model gives Belcher a slight nod at 63% — this could easily go either way.
Vagner Rocha vs Cody McKenzie
The Lightweight matchup features Vagner Rocha (1-2) taking on Cody McKenzie (3-3).
The Elo gap here is razor-thin — Rocha at 868, McKenzie at 871. On paper, this is as close to a coin flip as it gets.
A few statistical edges stand out. Rocha throws significantly more leather — a 1.7 sig. strike per minute gap. McKenzie is far more active with takedowns, averaging 2.9 more per 15 minutes. McKenzie has tighter striking defense, making opponents miss more often.
The Pick: Cody McKenzie over Vagner Rocha. The model gives McKenzie a slight nod at 64% — this could easily go either way.
Evan Dunham vs Shamar Bailey
The Lightweight matchup features Evan Dunham (11-8-1) taking on Shamar Bailey (1-1). Bailey will look to use a 5-inch reach edge to control distance.
There's a real Elo separation here: Dunham at 1019 versus Bailey at 897. That 123-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Dunham throws significantly more leather — a 0.9 sig. strike per minute gap. Bailey is far more active with takedowns, averaging 3.0 more per 15 minutes. Bailey has tighter striking defense, making opponents miss more often.
The Pick: Shamar Bailey over Evan Dunham. This is essentially a pick'em. The model nudges toward Bailey at 52%, but there's almost nothing separating these two.
Lance Benoist vs Matthew Riddle
The Welterweight matchup features Lance Benoist (1-2) taking on Matthew Riddle (7-3). Riddle is the bigger frame at 6'1" with a 4-inch reach advantage.
There's a real Elo separation here: Riddle at 1158 versus Benoist at 1024. That 135-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Riddle throws significantly more leather — a 3.1 sig. strike per minute gap. Riddle is far more active with takedowns, averaging 3.0 more per 15 minutes. Benoist has tighter striking defense, making opponents miss more often.
The Pick: Matthew Riddle over Lance Benoist. The model gives Riddle a slight nod at 57% — this could easily go either way.
Ken Stone vs Donny Walker
The Bantamweight matchup features Ken Stone (2-1) taking on Donny Walker (0-1).
Stone is rated at 959 — 168 points above Walker's 791. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Stone throws significantly more leather — a 2.4 sig. strike per minute gap. Walker is far more active with takedowns, averaging 0.0 more per 15 minutes. Walker has tighter striking defense, making opponents miss more often.
The Pick: Ken Stone over Donny Walker. The model gives Stone a slight nod at 55% — this could easily go either way.
Seth Baczynski vs Clay Harvison
The Welterweight matchup features Seth Baczynski (5-5) taking on Clay Harvison (1-1).
The Elo gap here is razor-thin — Baczynski at 796, Harvison at 805. On paper, this is as close to a coin flip as it gets.
A few statistical edges stand out. Harvison throws significantly more leather — a 2.3 sig. strike per minute gap. Harvison is far more active with takedowns, averaging 1.0 more per 15 minutes. Harvison has tighter striking defense, making opponents miss more often.
The Pick: Seth Baczynski over Clay Harvison. The model gives Baczynski a slight nod at 56% — this could easily go either way.
TJ Waldburger vs Mike Stumpf
The Welterweight matchup features TJ Waldburger (4-3) taking on Mike Stumpf (0-1).
Waldburger is rated at 1008 — 166 points above Stumpf's 842. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Waldburger throws significantly more leather — a 2.4 sig. strike per minute gap. Waldburger is far more active with takedowns, averaging 5.4 more per 15 minutes. Stumpf has tighter striking defense, making opponents miss more often.
The Pick: TJ Waldburger over Mike Stumpf. We're leaning Waldburger here at 67%, a solid but not overwhelming edge.
Robert Peralta vs Mike Lullo
The Featherweight matchup features Robert Peralta (4-2) taking on Mike Lullo (0-1).
Peralta is rated at 1039 — 222 points above Lullo's 817. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Lullo throws significantly more leather — a 1.1 sig. strike per minute gap. Lullo is far more active with takedowns, averaging 0.0 more per 15 minutes. Peralta has tighter striking defense, making opponents miss more often.
The Pick: Robert Peralta over Mike Lullo. The model gives Peralta a slight nod at 62% — this could easily go either way.
Justin Edwards vs Jorge Lopez
The Welterweight matchup features Justin Edwards (2-4) taking on Jorge Lopez (0-1).
Lopez carries a modest Elo edge (867 to 798), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
A few statistical edges stand out. Edwards throws significantly more leather — a 2.8 sig. strike per minute gap. Edwards is far more active with takedowns, averaging 7.0 more per 15 minutes. Lopez has tighter striking defense, making opponents miss more often.
The Pick: Justin Edwards over Jorge Lopez. The model gives Edwards a slight nod at 55% — this could easily go either way.
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.