UFC Fight Night: Maia vs LaFlare: Predictions & Analysis
UFC Fight Night: Maia vs LaFlare lands on Saturday, March 21, 2015 in Rio de Janeiro, Brazil with 12 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
| Matchup | Pick | Confidence | Prob |
|---|---|---|---|
| Demian Maia vs Ryan LaFlareWelterweight | Demian Maia | Toss-up | 52% |
| Erick Silva vs Josh KoscheckWelterweight | Erick Silva | Strong | 80% |
| Leonardo Santos vs Anthony Rocco MartinLightweight | Leonardo Santos | Toss-up | 51% |
| Amanda Nunes vs Shayna BaszlerWomen's Bantamweight | Amanda Nunes | Strong | 92% |
| Gilbert Burns vs Alex OliveiraLightweight | Gilbert Burns | Strong | 85% |
| Godofredo Pepey vs Andre FiliFeatherweight | Andre Fili | Strong | 76% |
| Francisco Trinaldo vs Akbarh ArreolaLightweight | Francisco Trinaldo | Toss-up | 53% |
| Edimilson Souza vs Katsunori KikunoFeatherweight | Edimilson Souza | Confident | 70% |
| Leandro Silva vs Drew DoberLightweight | Leandro Silva | Toss-up | 53% |
| Leonardo Mafra vs Cain CarrizosaLightweight | Leonardo Mafra | Toss-up | 52% |
| Christos Giagos vs Jorge de OliveiraLightweight | Christos Giagos | Strong | 75% |
| Fredy Serrano vs Bentley SylerFlyweight | Bentley Syler | Lean | 61% |
Fight-by-Fight Breakdown
Demian Maia vs Ryan LaFlare
The Welterweight championship matchup features Demian Maia (22-10) taking on Ryan LaFlare (7-2).
Maia is rated at 1371 — 197 points above LaFlare's 1174. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Maia's wrestler game against LaFlare's striker approach. Maia looks to close distance and put the fight on the mat, while LaFlare brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. LaFlare throws significantly more leather — a 2.4 sig. strike per minute gap. LaFlare is far more active with takedowns, averaging 1.2 more per 15 minutes. LaFlare has tighter striking defense, making opponents miss more often.
**The Pick: Demian Maia over Ryan LaFlare.** This is essentially a pick'em. The model nudges toward Maia at 52%, but there's almost nothing separating these two. Notably, the betting market has Maia at 45% implied while our model sees 52% — a 8-point disagreement that could signal value.
Erick Silva vs Josh Koscheck
The Welterweight matchup features Erick Silva (7-7) taking on Josh Koscheck (15-9).
The Elo gap here is razor-thin — Silva at 951, Koscheck at 939. On paper, this is as close to a coin flip as it gets.
The style clash matters here: Silva is most dangerous on the ground, constantly threatening chokes and joint locks, while Koscheck 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 Silva the stylistic edge.
A few statistical edges stand out. Silva throws significantly more leather — a 1.4 sig. strike per minute gap. Koscheck is far more active with takedowns, averaging 1.2 more per 15 minutes. Koscheck has tighter striking defense, making opponents miss more often.
**The Pick: Erick Silva over Josh Koscheck.** The model is firm on this one: Silva at 80%. The market and our model are aligned — the line looks fair.
Leonardo Santos vs Anthony Rocco Martin
The Lightweight matchup features Leonardo Santos (7-2-1) taking on Anthony Rocco Martin (9-5).
Martin is rated at 1419 — 380 points above Santos's 1039. Gaps this large usually mean one fighter has been consistently beating better opponents.
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. Santos throws significantly more leather — a 0.2 sig. strike per minute gap. Martin is far more active with takedowns, averaging 0.5 more per 15 minutes. Santos has tighter striking defense, making opponents miss more often.
**The Pick: Leonardo Santos over Anthony Rocco Martin.** This is essentially a pick'em. The model nudges toward Santos at 51%, but there's almost nothing separating these two.
Amanda Nunes vs Shayna Baszler
The Women's Bantamweight matchup features Amanda Nunes (15-2) taking on Shayna Baszler (0-1).
Nunes is rated at 1636 — 796 points above Baszler's 840. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Nunes throws significantly more leather — a 1.5 sig. strike per minute gap. Nunes is far more active with takedowns, averaging 1.3 more per 15 minutes. Nunes has tighter striking defense, making opponents miss more often.
**The Pick: Amanda Nunes over Shayna Baszler.** The model is firm on this one: Nunes at 92%. Notably, the betting market has Nunes at 80% implied while our model sees 92% — a 12-point disagreement that could signal value.
Gilbert Burns vs Alex Oliveira
The Lightweight matchup features Gilbert Burns (15-8) taking on Alex Oliveira (11-9). Oliveira will look to use a 5-inch reach edge to control distance.
Burns is rated at 1379 — 446 points above Oliveira's 934. Gaps this large usually mean one fighter has been consistently beating better opponents.
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. Burns throws significantly more leather — a 2.6 sig. strike per minute gap. Burns is far more active with takedowns, averaging 2.3 more per 15 minutes. Oliveira has tighter striking defense, making opponents miss more often.
**The Pick: Gilbert Burns over Alex Oliveira.** The model is firm on this one: Burns at 85%. The market and our model are aligned — the line looks fair.
Godofredo Pepey vs Andre Fili
The Featherweight matchup features Godofredo Pepey (5-5) taking on Andre Fili (12-11). There's a 4-inch height gap favoring Fili.
There's a real Elo separation here: Fili at 1140 versus Pepey at 1026. That 114-point gap typically reflects a meaningful difference in recent quality of competition and results.
Stylistically this is Pepey's wrestler game against Fili's striker approach. Pepey looks to close distance and put the fight on the mat, while Fili brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Fili throws significantly more leather — a 2.0 sig. strike per minute gap. Fili is far more active with takedowns, averaging 3.4 more per 15 minutes. Fili has tighter striking defense, making opponents miss more often.
**The Pick: Andre Fili over Godofredo Pepey.** The model is firm on this one: Fili at 76%. The market and our model are aligned — the line looks fair.
Francisco Trinaldo vs Akbarh Arreola
The Lightweight matchup features Francisco Trinaldo (18-7) taking on Akbarh Arreola (1-2).
Trinaldo is rated at 1329 — 455 points above Arreola's 875. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Arreola throws significantly more leather — a 0.2 sig. strike per minute gap. Arreola is far more active with takedowns, averaging 1.9 more per 15 minutes. Arreola has tighter striking defense, making opponents miss more often.
**The Pick: Francisco Trinaldo over Akbarh Arreola.** This is essentially a pick'em. The model nudges toward Trinaldo at 53%, but there's almost nothing separating these two. The market implies 65% for Trinaldo, but our model sees only 53%. That 12-point gap favoring Arreola is worth watching.
Edimilson Souza vs Katsunori Kikuno
The Featherweight matchup features Edimilson Souza (3-0) taking on Katsunori Kikuno (2-2). Souza is the bigger frame at 6'0" with a 8-inch reach advantage.
Souza is rated at 1166 — 219 points above Kikuno's 948. Gaps this large usually mean one fighter has been consistently beating better opponents. Souza rides a 3-fight win streak into this one.
A few statistical edges stand out. Souza throws significantly more leather — a 2.3 sig. strike per minute gap. Kikuno is far more active with takedowns, averaging 2.3 more per 15 minutes. Kikuno has tighter striking defense, making opponents miss more often.
**The Pick: Edimilson Souza over Katsunori Kikuno.** We're leaning Souza here at 70%, a solid but not overwhelming edge.
Leandro Silva vs Drew Dober
The Lightweight matchup features Leandro Silva (3-3) taking on Drew Dober (13-11).
Dober carries a modest Elo edge (1083 to 1049), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
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. Dober throws significantly more leather — a 1.3 sig. strike per minute gap. Silva is far more active with takedowns, averaging 2.2 more per 15 minutes. Dober has tighter striking defense, making opponents miss more often.
**The Pick: Leandro Silva over Drew Dober.** This is essentially a pick'em. The model nudges toward Silva at 53%, but there's almost nothing separating these two. The market implies 58% for Silva, but our model sees only 53%. That 5-point gap favoring Dober is worth watching.
Leonardo Mafra vs Cain Carrizosa
The Lightweight matchup features Leonardo Mafra (1-2) taking on Cain Carrizosa (0-1).
Mafra carries a modest Elo edge (864 to 795), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
A few statistical edges stand out. Mafra throws significantly more leather — a 2.5 sig. strike per minute gap. Carrizosa is far more active with takedowns, averaging 0.0 more per 15 minutes. Carrizosa has tighter striking defense, making opponents miss more often.
**The Pick: Leonardo Mafra over Cain Carrizosa.** This is essentially a pick'em. The model nudges toward Mafra at 52%, but there's almost nothing separating these two. The market implies 60% for Mafra, but our model sees only 52%. That 8-point gap favoring Carrizosa is worth watching.
Christos Giagos vs Jorge de Oliveira
The Lightweight matchup features Christos Giagos (6-7) taking on Jorge de Oliveira (0-1).
Giagos is rated at 940 — 156 points above Oliveira's 784. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Oliveira throws significantly more leather — a 0.7 sig. strike per minute gap. Oliveira is far more active with takedowns, averaging 0.0 more per 15 minutes. Oliveira has tighter striking defense, making opponents miss more often.
**The Pick: Christos Giagos over Jorge de Oliveira.** The model is firm on this one: Giagos at 75%.
Fredy Serrano vs Bentley Syler
The Flyweight matchup features Fredy Serrano (2-1) taking on Bentley Syler (0-0).
There's a real Elo separation here: Serrano at 984 versus Syler at 873. That 112-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Syler throws significantly more leather — a 0.0 sig. strike per minute gap. Syler is far more active with takedowns, averaging 0.0 more per 15 minutes. Syler has tighter striking defense, making opponents miss more often.
**The Pick: Bentley Syler over Fredy Serrano.** The model gives Syler a slight nod at 61% — 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.