UFC 215: Nunes vs Shevchenko 2: Predictions & Analysis

Saturday, September 9, 2017·Edmonton, Alberta, Canada
Published February 27, 2026
Predictions are for entertainment purposes only and do not constitute financial advice. Please gamble responsibly.

UFC 215: Nunes vs Shevchenko 2 lands on Saturday, September 9, 2017 in Edmonton, Alberta, Canada with 11 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
Amanda Nunes vs Valentina ShevchenkoWomen's BantamweightAmanda NunesToss-up52%
Rafael Dos Anjos vs Neil MagnyWelterweightRafael Dos AnjosLean56%
Henry Cejudo vs Wilson ReisFlyweightHenry CejudoStrong85%
Ilir Latifi vs Tyson PedroLight HeavyweightTyson PedroLean62%
Jeremy Stephens vs Gilbert MelendezFeatherweightJeremy StephensToss-up54%
Ketlen Vieira vs Sara McMannWomen's BantamweightKetlen VieiraLean56%
Sarah Moras vs Ashlee Evans-SmithWomen's BantamweightAshlee Evans-SmithConfident67%
Ricky Glenn vs Gavin TuckerFeatherweightRicky GlennToss-up55%
Alex White vs Mitch ClarkeLightweightAlex WhiteConfident73%
Arjan Bhullar vs Luis HenriqueHeavyweightArjan BhullarLean55%
Kajan Johnson vs Adriano MartinsLightweightAdriano MartinsStrong79%

Fight-by-Fight Breakdown

Amanda Nunes vs Valentina Shevchenko

Women's BantamweightTitle Fight
52%
Amanda Nunes
Nunes
15-2
Elo 1636
Wrestler
VS
Shevchenko
14-3-1
Elo 1797
All-Rounder

The Women's Bantamweight championship matchup features Amanda Nunes (15-2) taking on Valentina Shevchenko (14-3-1). Nunes is the bigger frame at 5'8" with a 3-inch reach advantage.

Shevchenko is rated at 1797 — 161 points above Nunes's 1636. Gaps this large usually mean one fighter has been consistently beating better opponents.

The style clash matters here: Nunes is most dangerous on the ground, constantly threatening chokes and joint locks, while Shevchenko is comfortable adjusting on the fly, mixing strikes and grappling as openings appear. In our database, submission artists own a 56% win rate against all-rounders, giving Nunes the stylistic edge.

A few statistical edges stand out. Nunes throws significantly more leather — a 3.7 sig. strike per minute gap. Shevchenko is far more active with takedowns, averaging 1.1 more per 15 minutes. Nunes has tighter striking defense, making opponents miss more often.

The Pick: Amanda Nunes over Valentina Shevchenko. This is essentially a pick'em. The model nudges toward Nunes at 52%, but there's almost nothing separating these two. Notably, the betting market has Nunes at 46% implied while our model sees 52% — a 6-point disagreement that could signal value.

56%
Rafael Dos Anjos
Anjos
21-14
Elo 1282
Wrestler
VS
Magny
24-12
Elo 1270
Wrestler

The Welterweight matchup features Rafael Dos Anjos (21-14) taking on Neil Magny (24-12). Magny is the bigger frame at 6'3" with a 10-inch reach advantage.

The Elo gap here is razor-thin — Anjos at 1282, Magny at 1270. On paper, this is as close to a coin flip as it gets.

The style clash matters here: Anjos is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Magny looks to close distance and put the fight on the mat. In our database, wrestlers own a 59% win rate against all-rounders, giving Magny the stylistic edge.

A few statistical edges stand out. Anjos throws significantly more leather — a 0.0 sig. strike per minute gap. Magny is far more active with takedowns, averaging 0.4 more per 15 minutes. Anjos has tighter striking defense, making opponents miss more often.

The Pick: Rafael Dos Anjos over Neil Magny. The model gives Anjos a slight nod at 56% — this could easily go either way.

85%
Henry Cejudo
Cejudo
10-5
Elo 1416
All-Rounder
VS
Reis
7-5
Elo 1083
Wrestler

The Flyweight matchup features Henry Cejudo (10-5) taking on Wilson Reis (7-5).

Cejudo is rated at 1416 — 333 points above Reis's 1083. 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. Cejudo throws significantly more leather — a 1.5 sig. strike per minute gap. Reis is far more active with takedowns, averaging 1.8 more per 15 minutes. Cejudo has tighter striking defense, making opponents miss more often.

The Pick: Henry Cejudo over Wilson Reis. The model is firm on this one: Cejudo at 85%. Notably, the betting market has Cejudo at 78% implied while our model sees 85% — a 8-point disagreement that could signal value.

Ilir Latifi vs Tyson Pedro

Light Heavyweight
62%
Tyson Pedro
Latifi
9-6
Elo 1195
Wrestler
VS
Pedro
6-4
Elo 1015
Knockout Artist

The Light Heavyweight matchup features Ilir Latifi (9-6) taking on Tyson Pedro (6-4). Pedro is the bigger frame at 6'3" with a 6-inch reach advantage.

Latifi is rated at 1195 — 180 points above Pedro's 1015. Gaps this large usually mean one fighter has been consistently beating better opponents.

The style clash matters here: Latifi is most dangerous on the ground, constantly threatening chokes and joint locks, while Pedro is patient on the feet, timing counters and loading up when he sees openings. In our database, knockout artists own a 54% win rate against submission artists, giving Pedro the stylistic edge.

A few statistical edges stand out. Pedro throws significantly more leather — a 1.3 sig. strike per minute gap. Pedro is far more active with takedowns, averaging 1.9 more per 15 minutes. Latifi has tighter striking defense, making opponents miss more often.

The Pick: Tyson Pedro over Ilir Latifi. The model gives Pedro a slight nod at 62% — this could easily go either way. The market implies 44% for Latifi, but our model sees only 38%. That 6-point gap favoring Pedro is worth watching.

54%
Jeremy Stephens
Stephens
15-18
Elo 941
Striker
VS
Melendez
1-5
Elo 976
Striker

The Featherweight matchup features Jeremy Stephens (15-18) taking on Gilbert Melendez (1-5).

Melendez carries a modest Elo edge (976 to 941), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

Stylistically this is Stephens's all-rounder game against Melendez's striker approach. Stephens is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Melendez brings a versatile approach. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. Stephens throws significantly more leather — a 0.1 sig. strike per minute gap. Melendez is far more active with takedowns, averaging 0.6 more per 15 minutes. Melendez has tighter striking defense, making opponents miss more often.

The Pick: Jeremy Stephens over Gilbert Melendez. This is essentially a pick'em. The model nudges toward Stephens at 54%, but there's almost nothing separating these two. Notably, the betting market has Stephens at 48% implied while our model sees 54% — a 6-point disagreement that could signal value.

Ketlen Vieira vs Sara McMann

Women's Bantamweight
56%
Ketlen Vieira
Vieira
9-4
Elo 1294
Wrestler
VS
McMann
6-6
Elo 1158
Wrestler

The Women's Bantamweight matchup features Ketlen Vieira (9-4) taking on Sara McMann (6-6). Vieira is the bigger frame at 5'8" with a 2-inch reach advantage.

There's a real Elo separation here: Vieira at 1294 versus McMann at 1158. That 136-point gap typically reflects a meaningful difference in recent quality of competition and results.

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. Vieira throws significantly more leather — a 0.9 sig. strike per minute gap. McMann is far more active with takedowns, averaging 0.0 more per 15 minutes. Vieira has tighter striking defense, making opponents miss more often.

The Pick: Ketlen Vieira over Sara McMann. The model gives Vieira a slight nod at 56% — this could easily go either way. Notably, the betting market has Vieira at 34% implied while our model sees 56% — a 22-point disagreement that could signal value.

Sarah Moras vs Ashlee Evans-Smith

Women's Bantamweight
67%
Ashlee Evans-Smith
Moras
3-5
Elo 808
Wrestler
VS
Evans-Smith
3-5
Elo 758
Striker

The Women's Bantamweight matchup features Sarah Moras (3-5) taking on Ashlee Evans-Smith (3-5).

Moras carries a modest Elo edge (808 to 758), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

Stylistically this is Moras's wrestler game against Evans-Smith's striker approach. Moras looks to close distance and put the fight on the mat, while Evans-Smith brings a versatile approach. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. Evans-Smith throws significantly more leather — a 3.2 sig. strike per minute gap. Evans-Smith is far more active with takedowns, averaging 0.8 more per 15 minutes. Evans-Smith has tighter striking defense, making opponents miss more often.

The Pick: Ashlee Evans-Smith over Sarah Moras. We're leaning Evans-Smith here at 67%, a solid but not overwhelming edge. Notably, the betting market has Moras at 29% implied while our model sees 33% — a 4-point disagreement that could signal value.

Ricky Glenn vs Gavin Tucker

Featherweight
55%
Ricky Glenn
Glenn
4-5-1
Elo 886
All-Rounder
VS
Tucker
4-2
Elo 1018
Wrestler

The Featherweight matchup features Ricky Glenn (4-5-1) taking on Gavin Tucker (4-2). Glenn is the bigger frame at 6'0" with a 4-inch reach advantage.

There's a real Elo separation here: Tucker at 1018 versus Glenn at 886. That 132-point gap typically reflects a meaningful difference in recent quality of competition and results.

The style clash matters here: Glenn is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Tucker looks to close distance and put the fight on the mat. In our database, wrestlers own a 59% win rate against all-rounders, giving Tucker the stylistic edge.

A few statistical edges stand out. Tucker throws significantly more leather — a 0.0 sig. strike per minute gap. Tucker is far more active with takedowns, averaging 1.0 more per 15 minutes. Tucker has tighter striking defense, making opponents miss more often.

The Pick: Ricky Glenn over Gavin Tucker. This is essentially a pick'em. The model nudges toward Glenn at 55%, but there's almost nothing separating these two.

Alex White vs Mitch Clarke

Lightweight
73%
Alex White
White
4-5
Elo 907
Knockout Artist
VS
Clarke
2-4
Elo 803
Wrestler

The Lightweight matchup features Alex White (4-5) taking on Mitch Clarke (2-4).

There's a real Elo separation here: White at 907 versus Clarke at 803. That 104-point gap typically reflects a meaningful difference in recent quality of competition and results.

The style clash matters here: White is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Clarke looks to close distance and put the fight on the mat. In our database, wrestlers own a 59% win rate against all-rounders, giving Clarke the stylistic edge.

A few statistical edges stand out. White throws significantly more leather — a 1.2 sig. strike per minute gap. White is far more active with takedowns, averaging 0.1 more per 15 minutes. White has tighter striking defense, making opponents miss more often.

The Pick: Alex White over Mitch Clarke. We're leaning White here at 73%, a solid but not overwhelming edge. Notably, the betting market has White at 66% implied while our model sees 73% — a 7-point disagreement that could signal value.

55%
Arjan Bhullar
Bhullar
2-1
Elo 1137
VS
Henrique
2-3
Elo 831
Wrestler

The Heavyweight matchup features Arjan Bhullar (2-1) taking on Luis Henrique (2-3).

Bhullar is rated at 1137 — 306 points above Henrique's 831. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Henrique throws significantly more leather — a 1.6 sig. strike per minute gap. Henrique is far more active with takedowns, averaging 3.9 more per 15 minutes. Bhullar has tighter striking defense, making opponents miss more often.

The Pick: Arjan Bhullar over Luis Henrique. The model gives Bhullar a slight nod at 55% — this could easily go either way. The market implies 66% for Bhullar, but our model sees only 55%. That 10-point gap favoring Henrique is worth watching.

79%
Adriano Martins
Johnson
4-2
Elo 1168
All-Rounder
VS
Martins
4-2
Elo 1070
All-Rounder

The Lightweight matchup features Kajan Johnson (4-2) taking on Adriano Martins (4-2). Johnson will look to use a 3-inch reach edge to control distance.

There's a real Elo separation here: Johnson at 1168 versus Martins at 1070. That 98-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. Johnson throws significantly more leather — a 0.7 sig. strike per minute gap. Johnson is far more active with takedowns, averaging 1.3 more per 15 minutes. Martins has tighter striking defense, making opponents miss more often.

The Pick: Adriano Martins over Kajan Johnson. The model is firm on this one: Martins at 79%. 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.