UFC Fight Night: Adesanya vs. Pyfer: Predictions & Analysis

Saturday, March 28, 2026·Seattle, Washington, USA
Published February 28, 2026
Predictions are for entertainment purposes only and do not constitute financial advice. Please gamble responsibly.

UFC Fight Night: Adesanya vs. Pyfer lands on Saturday, March 28, 2026 in Seattle, Washington, 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

MatchupPickConfidenceProb
Israel Adesanya vs Joe PyferMiddleweightJoe PyferToss-up52%
Alexa Grasso vs Maycee BarberWomen's FlyweightAlexa GrassoToss-up53%
Chase Hooper vs Lance Gibson Jr.LightweightChase HooperToss-up50%
Navajo Stirling vs Bruno LopesLight HeavyweightNavajo StirlingLean59%
Marcin Tybura vs Valter WalkerHeavyweightValter WalkerConfident68%
Michael Chiesa vs Carlston HarrisWelterweightMichael ChiesaLean57%
Mansur Abdul-Malik vs Yousri BelgarouiMiddleweightYousri BelgarouiLean60%
Casey O'Neill vs Gabriella FernandesWomen's FlyweightCasey O'NeillLean58%
Julian Erosa vs Lerryan DouglasFeatherweightJulian ErosaToss-up55%
Zhu Kangjie vs Marcio BarbosaFeatherweightZhu KangjieToss-up50%
Carol Foro vs Stephanie LucianoWomen's StrawweightStephanie LucianoLean55%
Terrance McKinney vs Kyle NelsonLightweightTerrance McKinneyToss-up51%

Fight-by-Fight Breakdown

Israel Adesanya vs Joe Pyfer

Middleweight
52%
Joe Pyfer
Adesanya
13-5
CO-I1559
Striker
VS
Pyfer
6-1
CO-I1530
All-Rounder
Method Prediction
KO 44%Sub 23%Dec 33%

The Middleweight matchup features Israel Adesanya (13-5) taking on Joe Pyfer (6-1). Adesanya is the bigger frame at 6'4" with a 5-inch reach advantage.

The Elo gap here is razor-thin — Adesanya at 1559, Pyfer at 1530. On paper, this is as close to a coin flip as it gets. Pyfer has won 3 straight.

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

A few statistical edges stand out. Adesanya throws significantly more leather — a 0.8 sig. strike per minute gap. Pyfer is far more active with takedowns, averaging 0.9 more per 15 minutes. Pyfer has tighter striking defense, making opponents miss more often.

There's a real chance this one doesn't go the distance — our model sees a 44% probability of a KO/TKO finish, with 23% submission and 33% decision.

The Pick: Joe Pyfer over Israel Adesanya. This is essentially a pick'em. The model nudges toward Pyfer at 52%, but there's almost nothing separating these two.

Alexa Grasso vs Maycee Barber

Women's Flyweight
53%
Alexa Grasso
Grasso
8-4-1
CO-II1376
All-Rounder
VS
Barber
10-2
CO-I1543
Striker
Method Prediction
KO 25%Sub 35%Dec 40%

The Women's Flyweight matchup features Alexa Grasso (8-4-1) taking on Maycee Barber (10-2).

Barber is rated at 1543 — 167 points above Grasso's 1376. Gaps this large usually mean one fighter has been consistently beating better opponents. Barber has won 7 straight.

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

The submission threat is elevated here at 35%, with the model also seeing 25% KO/TKO and 40% decision probability.

The Pick: Alexa Grasso over Maycee Barber. This is essentially a pick'em. The model nudges toward Grasso at 53%, but there's almost nothing separating these two.

50%
Chase Hooper
Hooper
8-4
RK-I1175
Submission Artist
VS
Jr.
0-1
MC-II957
Method Prediction
KO 23%Sub 41%Dec 36%

The Lightweight matchup features Chase Hooper (8-4) taking on Lance Gibson Jr. (0-1). Hooper is the bigger frame at 6'1" with a 2-inch reach advantage.

Hooper is rated at 1175 — 218 points above Jr.'s 957. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Hooper throws significantly more leather — a 1.2 sig. strike per minute gap. Hooper is far more active with takedowns, averaging 3.2 more per 15 minutes. Hooper has tighter striking defense, making opponents miss more often.

The submission threat is elevated here at 41%, with the model also seeing 23% KO/TKO and 36% decision probability.

The Pick: Chase Hooper over Lance Gibson Jr.. This is essentially a pick'em. The model nudges toward Hooper at 50%, but there's almost nothing separating these two.

Navajo Stirling vs Bruno Lopes

Light Heavyweight
59%
Navajo Stirling
Stirling
3-0
CO-III1202
VS
Lopes
1-0
RK-III1029
Method Prediction
KO 44%Sub 36%Dec 20%

The Light Heavyweight matchup features Navajo Stirling (3-0) taking on Bruno Lopes (1-0). Stirling is the bigger frame at 6'4" with a 5-inch reach advantage.

Stirling is rated at 1202 — 172 points above Lopes's 1029. Gaps this large usually mean one fighter has been consistently beating better opponents. Stirling rides a 3-fight win streak into this one.

There's a real chance this one doesn't go the distance — our model sees a 44% probability of a KO/TKO finish, with 36% submission and 20% decision.

The Pick: Navajo Stirling over Bruno Lopes. The model gives Stirling a slight nod at 59% — this could easily go either way.

68%
Valter Walker
Tybura
14-9
CO-III1242
Wrestler
VS
Walker
4-1
CO-III1314
Method Prediction
KO 45%Sub 25%Dec 30%

The Heavyweight matchup features Marcin Tybura (14-9) taking on Valter Walker (4-1). There's a 3-inch height gap favoring Walker.

Walker carries a modest Elo edge (1314 to 1242), the kind of gap that reflects a slightly better run of form rather than a talent chasm. Walker has won 4 straight.

A few statistical edges stand out. Tybura throws significantly more leather — a 1.9 sig. strike per minute gap. Walker is far more active with takedowns, averaging 4.4 more per 15 minutes. Tybura has tighter striking defense, making opponents miss more often.

There's a real chance this one doesn't go the distance — our model sees a 45% probability of a KO/TKO finish, with 25% submission and 30% decision.

The Pick: Valter Walker over Marcin Tybura. We're leaning Walker here at 68%, a solid but not overwhelming edge.

57%
Michael Chiesa
Chiesa
13-7
CO-I1490
Wrestler
VS
Harris
4-2
RK-II1097
Wrestler
Method Prediction
KO 26%Sub 48%Dec 26%

The Welterweight matchup features Michael Chiesa (13-7) taking on Carlston Harris (4-2).

Chiesa is rated at 1490 — 394 points above Harris's 1097. 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.

The submission threat is elevated here at 48%, with the model also seeing 26% KO/TKO and 26% decision probability.

The Pick: Michael Chiesa over Carlston Harris. The model gives Chiesa a slight nod at 57% — this could easily go either way.

60%
Yousri Belgaroui
Abdul-Malik
3-0
CO-III1208
VS
Belgaroui
1-0
CO-III1210
Method Prediction
KO 29%Sub 25%Dec 46%

The Middleweight matchup features Mansur Abdul-Malik (3-0) taking on Yousri Belgaroui (1-0). There's a 4-inch height gap favoring Belgaroui.

The Elo gap here is razor-thin — Abdul-Malik at 1208, Belgaroui at 1210. On paper, this is as close to a coin flip as it gets.

A few statistical edges stand out. Belgaroui throws significantly more leather — a 5.6 sig. strike per minute gap. Belgaroui is far more active with takedowns, averaging 0.1 more per 15 minutes. Belgaroui has tighter striking defense, making opponents miss more often.

The submission threat is elevated here at 25%, with the model also seeing 29% KO/TKO and 46% decision probability.

The Pick: Yousri Belgaroui over Mansur Abdul-Malik. The model gives Belgaroui a slight nod at 60% — this could easily go either way.

58%
Casey O'Neill
O'Neill
4-2
RK-I1172
All-Rounder
VS
Fernandes
2-2
RK-II1122
Method Prediction
KO 23%Sub 44%Dec 33%

The Women's Flyweight matchup features Casey O'Neill (4-2) taking on Gabriella Fernandes (2-2). O'Neill will look to use a 3-inch reach edge to control distance.

O'Neill carries a modest Elo edge (1172 to 1122), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

The submission threat is elevated here at 44%, with the model also seeing 23% KO/TKO and 33% decision probability.

The Pick: Casey O'Neill over Gabriella Fernandes. The model gives O'Neill a slight nod at 58% — this could easily go either way.

55%
Julian Erosa
Erosa
9-7
CO-III1280
Knockout Artist
VS
Douglas
0-0
RK-III1000
Method Prediction
KO 30%Sub 38%Dec 32%

The Featherweight matchup features Julian Erosa (9-7) taking on Lerryan Douglas (0-0). Erosa is the bigger frame at 6'1" with a 2-inch reach advantage.

Erosa is rated at 1280 — 280 points above Douglas's 1000. Gaps this large usually mean one fighter has been consistently beating better opponents. Erosa rides a 3-fight win streak into this one.

The submission threat is elevated here at 38%, with the model also seeing 30% KO/TKO and 32% decision probability.

The Pick: Julian Erosa over Lerryan Douglas. This is essentially a pick'em. The model nudges toward Erosa at 55%, but there's almost nothing separating these two.

Zhu Kangjie vs Marcio Barbosa

Featherweight
50%
Zhu Kangjie
Kangjie
0-0
RK-III1000
VS
Barbosa
0-0
RK-III1000
Method Prediction
KO 21%Sub 44%Dec 35%

The Featherweight matchup features Zhu Kangjie (0-0) taking on Marcio Barbosa (0-0).

The Elo gap here is razor-thin — Kangjie at 1000, Barbosa at 1000. On paper, this is as close to a coin flip as it gets.

The submission threat is elevated here at 44%, with the model also seeing 21% KO/TKO and 35% decision probability.

The Pick: Zhu Kangjie over Marcio Barbosa. This is essentially a pick'em. The model nudges toward Kangjie at 50%, but there's almost nothing separating these two.

Carol Foro vs Stephanie Luciano

Women's Strawweight
55%
Stephanie Luciano
Foro
0-0
RK-III1000
VS
Luciano
2-1
RK-II1105
Method Prediction
KO 18%Sub 44%Dec 38%

The Women's Strawweight matchup features Carol Foro (0-0) taking on Stephanie Luciano (2-1). Luciano is the bigger frame at 5'6" with a 4-inch reach advantage.

There's a real Elo separation here: Luciano at 1105 versus Foro at 1000. That 105-point gap typically reflects a meaningful difference in recent quality of competition and results.

The submission threat is elevated here at 44%, with the model also seeing 18% KO/TKO and 37% decision probability.

The Pick: Stephanie Luciano over Carol Foro. The model gives Luciano a slight nod at 55% — this could easily go either way.

51%
Terrance McKinney
McKinney
7-5
RK-II1110
Submission Artist
VS
Nelson
5-5-1
CO-III1271
Striker
Method Prediction
KO 36%Sub 32%Dec 32%

The Lightweight matchup features Terrance McKinney (7-5) taking on Kyle Nelson (5-5-1).

Nelson is rated at 1271 — 161 points above McKinney's 1110. Gaps this large usually mean one fighter has been consistently beating better opponents.

Stylistically this is McKinney's submission artist game against Nelson's striker approach. McKinney is most dangerous on the ground, constantly threatening chokes and joint locks, while Nelson brings a versatile approach. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. McKinney throws significantly more leather — a 12.0 sig. strike per minute gap. McKinney is far more active with takedowns, averaging 1.8 more per 15 minutes. Nelson has tighter striking defense, making opponents miss more often.

There's a real chance this one doesn't go the distance — our model sees a 36% probability of a KO/TKO finish, with 32% submission and 33% decision.

The Pick: Terrance McKinney over Kyle Nelson. This is essentially a pick'em. The model nudges toward McKinney at 51%, but there's almost nothing separating these two.

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.