UFC 64: Unstoppable: Predictions & Analysis

Saturday, October 14, 2006·Las Vegas, Nevada, USA
Published February 27, 2026
Predictions are for entertainment purposes only and do not constitute financial advice. Please gamble responsibly.

UFC 64: Unstoppable lands on Saturday, October 14, 2006 in Las Vegas, Nevada, USA with 8 bouts on the card. The card is headlined by a championship fight. 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

MatchupPickConfidenceProb
Anderson Silva vs Rich FranklinMiddleweightAnderson SilvaToss-up52%
Sean Sherk vs Kenny FlorianLightweightKenny FlorianToss-up53%
Jon Fitch vs Kuniyoshi HironakaWelterweightJon FitchConfident70%
Carmelo Marrero vs Cheick KongoHeavyweightCheick KongoStrong76%
Spencer Fisher vs Dan LauzonLightweightSpencer FisherConfident71%
Yushin Okami vs Kalib StarnesMiddleweightYushin OkamiLean59%
Clay Guida vs Justin JamesLightweightClay GuidaToss-up53%
Kurt Pellegrino vs Junior AssuncaoLightweightKurt PellegrinoLean62%

Fight-by-Fight Breakdown

52%
Anderson Silva
Silva
17-6
Elo 1154
All-Rounder
VS
Franklin
14-5
Elo 1094
All-Rounder

The Middleweight matchup features Anderson Silva (17-6) taking on Rich Franklin (14-5).

Silva carries a modest Elo edge (1154 to 1094), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

Stylistically this is Silva's all-rounder game against Franklin's knockout artist approach. Silva is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Franklin is patient on the feet, timing counters and loading up when he sees openings. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. Silva throws significantly more leather — a 16.1 sig. strike per minute gap. Franklin is far more active with takedowns, averaging 1.9 more per 15 minutes. Silva has tighter striking defense, making opponents miss more often.

The Pick: Anderson Silva over Rich Franklin. This is essentially a pick'em. The model nudges toward Silva at 52%, but there's almost nothing separating these two.

Sean Sherk vs Kenny Florian

LightweightTitle Fight
53%
Kenny Florian
Sherk
7-4
Elo 1371
Wrestler
VS
Florian
12-4
Elo 1304
Wrestler

The Lightweight championship matchup features Sean Sherk (7-4) taking on Kenny Florian (12-4). Florian is the bigger frame at 5'10" with a 7-inch reach advantage.

Sherk carries a modest Elo edge (1371 to 1304), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

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. Florian throws significantly more leather — a 1.5 sig. strike per minute gap. Florian is far more active with takedowns, averaging 1.3 more per 15 minutes. Florian has tighter striking defense, making opponents miss more often.

The Pick: Kenny Florian over Sean Sherk. This is essentially a pick'em. The model nudges toward Florian at 53%, but there's almost nothing separating these two.

70%
Jon Fitch
Fitch
14-2-1
Elo 1398
Wrestler
VS
Hironaka
1-2
Elo 878

The Welterweight matchup features Jon Fitch (14-2-1) taking on Kuniyoshi Hironaka (1-2). Fitch is the bigger frame at 6'0" with a 4-inch reach advantage.

Fitch is rated at 1398 — 520 points above Hironaka's 878. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Fitch throws significantly more leather — a 2.9 sig. strike per minute gap. Fitch is far more active with takedowns, averaging 4.8 more per 15 minutes. Hironaka has tighter striking defense, making opponents miss more often.

The Pick: Jon Fitch over Kuniyoshi Hironaka. We're leaning Fitch here at 70%, a solid but not overwhelming edge.

76%
Cheick Kongo
Marrero
1-2
Elo 890
VS
Kongo
11-5-1
Elo 1183
Striker

The Heavyweight matchup features Carmelo Marrero (1-2) taking on Cheick Kongo (11-5-1). Kongo is the bigger frame at 6'4" with a 9-inch reach advantage.

Kongo is rated at 1183 — 293 points above Marrero's 890. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Kongo throws significantly more leather — a 5.8 sig. strike per minute gap. Kongo is far more active with takedowns, averaging 2.1 more per 15 minutes. Marrero has tighter striking defense, making opponents miss more often.

The Pick: Cheick Kongo over Carmelo Marrero. The model is firm on this one: Kongo at 76%.

71%
Spencer Fisher
Fisher
9-7
Elo 876
All-Rounder
VS
Lauzon
0-2
Elo 828

The Lightweight matchup features Spencer Fisher (9-7) taking on Dan Lauzon (0-2).

Fisher carries a modest Elo edge (876 to 828), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

A few statistical edges stand out. Fisher throws significantly more leather — a 3.2 sig. strike per minute gap. Fisher is far more active with takedowns, averaging 2.1 more per 15 minutes. Lauzon has tighter striking defense, making opponents miss more often.

The Pick: Spencer Fisher over Dan Lauzon. We're leaning Fisher here at 71%, a solid but not overwhelming edge.

59%
Yushin Okami
Okami
14-6
Elo 1061
Wrestler
VS
Starnes
2-2
Elo 936

The Middleweight matchup features Yushin Okami (14-6) taking on Kalib Starnes (2-2).

There's a real Elo separation here: Okami at 1061 versus Starnes at 936. That 126-point gap typically reflects a meaningful difference in recent quality of competition and results.

A few statistical edges stand out. Starnes throws significantly more leather — a 6.4 sig. strike per minute gap. Starnes is far more active with takedowns, averaging 0.1 more per 15 minutes. Okami has tighter striking defense, making opponents miss more often.

The Pick: Yushin Okami over Kalib Starnes. The model gives Okami a slight nod at 59% — this could easily go either way.

Clay Guida vs Justin James

Lightweight
53%
Clay Guida
Guida
18-18
Elo 926
All-Rounder
VS
James
0-0
Elo 890

The Lightweight matchup features Clay Guida (18-18) taking on Justin James (0-0).

Guida carries a modest Elo edge (926 to 890), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

A few statistical edges stand out. James throws significantly more leather — a 0.0 sig. strike per minute gap. James is far more active with takedowns, averaging 0.0 more per 15 minutes. James has tighter striking defense, making opponents miss more often.

The Pick: Clay Guida over Justin James. This is essentially a pick'em. The model nudges toward Guida at 53%, but there's almost nothing separating these two.

62%
Kurt Pellegrino
Pellegrino
7-4
Elo 1215
Wrestler
VS
Assuncao
2-2
Elo 963

The Lightweight matchup features Kurt Pellegrino (7-4) taking on Junior Assuncao (2-2).

Pellegrino is rated at 1215 — 253 points above Assuncao's 963. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Pellegrino throws significantly more leather — a 2.2 sig. strike per minute gap. Pellegrino is far more active with takedowns, averaging 6.6 more per 15 minutes. Assuncao has tighter striking defense, making opponents miss more often.

The Pick: Kurt Pellegrino over Junior Assuncao. The model gives Pellegrino a slight nod at 62% — 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.