UFC Fight Night: Rockhold vs. Branch: Predictions & Analysis
UFC Fight Night: Rockhold vs. Branch lands on Saturday, September 16, 2017 in Pittsburgh, Pennsylvania, USA with 10 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 |
|---|---|---|---|
| Luke Rockhold vs David BranchMiddleweight | Luke Rockhold | Confident | 70% |
| Mike Perry vs Alex ReyesWelterweight | Mike Perry | Strong | 88% |
| Anthony Smith vs Hector LombardMiddleweight | Anthony Smith | Lean | 59% |
| Gregor Gillespie vs Jason GonzalezLightweight | Gregor Gillespie | Strong | 88% |
| Kamaru Usman vs Sergio MoraesWelterweight | Kamaru Usman | Strong | 86% |
| Justin Ledet vs Azunna AnyanwuHeavyweight | Justin Ledet | Strong | 93% |
| Olivier Aubin-Mercier vs Anthony Rocco MartinLightweight | Olivier Aubin-Mercier | Confident | 68% |
| Daniel Spitz vs Anthony HamiltonHeavyweight | Anthony Hamilton | Lean | 57% |
| Uriah Hall vs Krzysztof JotkoMiddleweight | Krzysztof Jotko | Lean | 65% |
| Gilbert Burns vs Jason SaggoLightweight | Gilbert Burns | Lean | 56% |
Fight-by-Fight Breakdown
Luke Rockhold vs David Branch
The Middleweight matchup features Luke Rockhold (6-4) taking on David Branch (4-4).
Rockhold is rated at 1302 — 166 points above Branch's 1136. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Rockhold's submission artist game against Branch's striker approach. Rockhold is most dangerous on the ground, constantly threatening chokes and joint locks, while Branch brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Rockhold throws significantly more leather — a 3.6 sig. strike per minute gap. Branch is far more active with takedowns, averaging 1.1 more per 15 minutes. Branch has tighter striking defense, making opponents miss more often.
The Pick: Luke Rockhold over David Branch. We're leaning Rockhold here at 70%, a solid but not overwhelming edge. The market implies 82% for Rockhold, but our model sees only 70%. That 12-point gap favoring Branch is worth watching.
Mike Perry vs Alex Reyes
The Welterweight matchup features Mike Perry (7-7) taking on Alex Reyes (0-2).
Perry is rated at 1066 — 268 points above Reyes's 798. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Perry throws significantly more leather — a 4.7 sig. strike per minute gap. Reyes is far more active with takedowns, averaging 0.0 more per 15 minutes. Reyes has tighter striking defense, making opponents miss more often.
The Pick: Mike Perry over Alex Reyes. The model is firm on this one: Perry at 88%. Notably, the betting market has Perry at 81% implied while our model sees 88% — a 7-point disagreement that could signal value.
Anthony Smith vs Hector Lombard
The Middleweight matchup features Anthony Smith (13-11) taking on Hector Lombard (3-7). Smith is the bigger frame at 6'4" with a 5-inch reach advantage.
There's a real Elo separation here: Smith at 1070 versus Lombard at 964. That 106-point gap typically reflects a meaningful difference in recent quality of competition and results.
Both fighters land in our "All-Rounder" archetype — fighters comfortable everywhere, able to strike or grapple depending on what the opponent gives them. 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. Smith throws significantly more leather — a 0.3 sig. strike per minute gap. Lombard is far more active with takedowns, averaging 2.3 more per 15 minutes. Lombard has tighter striking defense, making opponents miss more often.
The Pick: Anthony Smith over Hector Lombard. The model gives Smith a slight nod at 59% — this could easily go either way. The market and our model are aligned — the line looks fair.
Gregor Gillespie vs Jason Gonzalez
The Lightweight matchup features Gregor Gillespie (6-1) taking on Jason Gonzalez (1-2). Gonzalez is the bigger frame at 6'2" with a 3-inch reach advantage.
Gillespie is rated at 1554 — 667 points above Gonzalez's 887. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Gillespie throws significantly more leather — a 0.7 sig. strike per minute gap. Gillespie is far more active with takedowns, averaging 4.9 more per 15 minutes. Gillespie has tighter striking defense, making opponents miss more often.
The Pick: Gregor Gillespie over Jason Gonzalez. The model is firm on this one: Gillespie at 88%. Notably, the betting market has Gillespie at 79% implied while our model sees 88% — a 9-point disagreement that could signal value.
Kamaru Usman vs Sergio Moraes
The Welterweight matchup features Kamaru Usman (15-3) taking on Sergio Moraes (8-4-1). Usman will look to use a 4-inch reach edge to control distance.
Usman is rated at 1828 — 732 points above Moraes's 1097. Gaps this large usually mean one fighter has been consistently beating better opponents.
The style clash matters here: Usman looks to close distance and put the fight on the mat, while Moraes is comfortable adjusting on the fly, mixing strikes and grappling as openings appear. In our database, wrestlers own a 59% win rate against all-rounders, giving Usman the stylistic edge.
A few statistical edges stand out. Usman throws significantly more leather — a 1.6 sig. strike per minute gap. Usman is far more active with takedowns, averaging 3.9 more per 15 minutes. Moraes has tighter striking defense, making opponents miss more often.
The Pick: Kamaru Usman over Sergio Moraes. The model is firm on this one: Usman at 86%. The market and our model are aligned — the line looks fair.
Justin Ledet vs Azunna Anyanwu
The Heavyweight matchup features Justin Ledet (3-3) taking on Azunna Anyanwu (0-0).
Anyanwu is rated at 963 — 207 points above Ledet's 756. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Ledet throws significantly more leather — a 6.7 sig. strike per minute gap. Ledet is far more active with takedowns, averaging 0.9 more per 15 minutes. Anyanwu has tighter striking defense, making opponents miss more often.
The Pick: Justin Ledet over Azunna Anyanwu. The model is firm on this one: Ledet at 93%. Notably, the betting market has Ledet at 79% implied while our model sees 93% — a 14-point disagreement that could signal value.
Olivier Aubin-Mercier vs Anthony Rocco Martin
The Lightweight matchup features Olivier Aubin-Mercier (7-4) taking on Anthony Rocco Martin (9-5). Martin is the bigger frame at 6'0" with a 3-inch reach advantage.
Martin is rated at 1419 — 349 points above Aubin-Mercier's 1070. Gaps this large usually mean one fighter has been consistently beating better opponents.
Both fighters land in our "Wrestler" archetype — fighters who win by dictating where the fight takes place, grinding out control time and wearing opponents down. 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. Martin throws significantly more leather — a 0.5 sig. strike per minute gap. Aubin-Mercier is far more active with takedowns, averaging 1.5 more per 15 minutes. Martin has tighter striking defense, making opponents miss more often.
The Pick: Olivier Aubin-Mercier over Anthony Rocco Martin. We're leaning Aubin-Mercier here at 68%, a solid but not overwhelming edge.
Daniel Spitz vs Anthony Hamilton
The Heavyweight matchup features Daniel Spitz (1-2) taking on Anthony Hamilton (3-6). Spitz is the bigger frame at 6'7" with a 6-inch reach advantage.
There's a real Elo separation here: Spitz at 858 versus Hamilton at 722. That 136-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Hamilton throws significantly more leather — a 0.7 sig. strike per minute gap. Hamilton is far more active with takedowns, averaging 0.7 more per 15 minutes. Spitz has tighter striking defense, making opponents miss more often.
The Pick: Anthony Hamilton over Daniel Spitz. The model gives Hamilton a slight nod at 57% — this could easily go either way. Notably, the betting market has Spitz at 35% implied while our model sees 43% — a 8-point disagreement that could signal value.
Uriah Hall vs Krzysztof Jotko
The Middleweight matchup features Uriah Hall (10-8) taking on Krzysztof Jotko (11-5).
Hall is rated at 1378 — 156 points above Jotko's 1222. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Hall's all-rounder game against Jotko's striker approach. Hall is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Jotko brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Hall throws significantly more leather — a 0.2 sig. strike per minute gap. Jotko is far more active with takedowns, averaging 1.0 more per 15 minutes. Jotko has tighter striking defense, making opponents miss more often.
The Pick: Krzysztof Jotko over Uriah Hall. The model gives Jotko a slight nod at 65% — this could easily go either way.
Gilbert Burns vs Jason Saggo
The Lightweight matchup features Gilbert Burns (15-8) taking on Jason Saggo (3-2).
Burns is rated at 1379 — 366 points above Saggo's 1013. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Burns's wrestler game against Saggo's striker approach. Burns looks to close distance and put the fight on the mat, while Saggo brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Saggo throws significantly more leather — a 0.3 sig. strike per minute gap. Saggo is far more active with takedowns, averaging 0.5 more per 15 minutes. Burns has tighter striking defense, making opponents miss more often.
The Pick: Gilbert Burns over Jason Saggo. The model gives Burns a slight nod at 56% — this could easily go either way. The market and our model are aligned — the line looks fair.
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.