NBA Picks for October 31: SA 80% Leads a 7-Game Board

7 NBA games on the board for 2026-10-31. The firmest call is SA at 80% over MIN; the model and the market are 3 points or more apart on 2. Season to date the model is 55-28 (66.3%) on graded picks, Brier 0.205.

Every number here is the model's own: win probabilities from the point-in-time model blended with the market, the drivers from its feature breakdown, the player lines from the same projections that build the DFS slates, and the crew notes from the referee tables. A player line is the point where our distribution gives that side 57%: the over is a play at that line or lower, the under at that line or higher, at -120 or better.

The board

The pick is the more likely winner (the model blended with the market). The Model Card leg is a different question: the side whose price beats the model's own number. In a close game they can point at different teams; both are shown, and both are graded.

Where the model and the market disagree

The market is more confident than we are on these. We still expect the favourite to win, but on our numbers the other side carries the value at the market's price:

CLE over MIL: we make it 72%, the market 76% (a 4-point gap).

POR over UTAH: we make it 68%, the market 74% (a 7-point gap).

Game by game

Minnesota Timberwolves at San Antonio Spurs: SA 80%

The model has SA at 80% against a market price of 82%. What drives it: injuries (sa without harris; min without edwards, divincenzo) (+5.2 points), preseason prior (season-win futures, 5 and 6 games in) (+4.5 points), head to head (+2.6 points). The case against is venue (-4.1 points). The line is SA -12.5, total 227.5.

MIN out: Anthony Edwards, Donte DiVincenzo. SA out: Jayden Quaintance, Tobias Harris.

Sacramento Kings at Memphis Grizzlies: MEM 74%

The model has MEM at 74% against a market price of 75%. What drives it: net rating, last 10 (+3.0 points), injuries (mem: pippen questionable, jerome, post day-to-day; sac without murray, raynaud, cardwell) (+2.8 points), head to head (+2.4 points). The case against is preseason prior (season-win futures, 5 and 5 games in) (-7.9 points). The line is MEM -8.5, total 230.5.

SAC out: Ben Simmons, Dylan Cardwell, Keegan Murray, Maxime Raynaud.

Cleveland Cavaliers at Milwaukee Bucks: CLE 72%

The model has CLE at 72% against a market price of 76%. What drives it: head to head (+6.8 points), preseason prior (season-win futures, 5 and 5 games in) (+2.7 points), home/road split (+2.2 points). The case against is venue (-6.3 points). The line is CLE -9.5, total 235.5. That is a 4-point gap to the market, so the market likes this side more than we do; treat the pick as a lean.

CLE out: Jaylon Tyson.

Portland Trail Blazers at Utah Jazz: POR 68%

The model has POR at 68% against a market price of 74%. What drives it: head to head (+6.5 points), venue (+5.4 points), net rating, last 10 (+5.2 points). The case against is preseason prior (season-win futures, 5 and 4 games in) (-15.1 points). The line is POR -8.5, total 232.5. That is a 7-point gap to the market, so the market likes this side more than we do; treat the pick as a lean.

POR out: Chris Youngblood, Ja Morant, Shaedon Sharpe. UTAH out: Jaren Jackson Jr., Jusuf Nurkic, Trey Alexander.

Atlanta Hawks at New Orleans Pelicans: ATL 62%

The model has ATL at 62% against a market price of 62%. What drives it: head to head (+7.0 points), venue (+5.1 points), injuries (no without poole, missi; atl without gueye) (+2.6 points). The case against is net rating, last 10 (-2.5 points). The line is ATL -4.5, total 240.5.

ATL out: Henri Veesaar, Mouhamed Gueye. NO out: Jordan Poole, Yves Missi.

Oklahoma City Thunder at Houston Rockets: HOU 54%

The model has HOU at 54% against a market price of 56%. What drives it: injuries (hou without adams; sengun, sheppard day-to-day; okc without holmgren, williams, wallace) (+6.3 points), net rating, last 10 (+5.5 points), star availability (+3.7 points). The case against is preseason prior (season-win futures, 6 and 5 games in) (-4.1 points). The line is HOU -2.5, total 218.5.

OKC out: Alex Caruso, Cason Wallace, Chet Holmgren, Jalen Williams, Nikola Topic. HOU out: Steven Adams.

Philadelphia 76ers at Charlotte Hornets: PHI 51%

The model has PHI at 51% against a market price of 53%. What drives it: venue (+8.9 points), head to head (+8.8 points), preseason prior (season-win futures, 6 and 6 games in) (+6.9 points). The case against is injuries (cha without knueppel, white, williams; phi without brown, barlow, walker; embiid, james day-to-day) (-6.2 points). The line is PHI -1.5, total 215.5. That is a 3-point gap to the market, so the market likes this side more than we do; treat the pick as a lean.

PHI out: Ariel Hukporti, Dominick Barlow, Jabari Walker, Tacko Fall. CHA out: Coby White, Grant Williams, Kon Knueppel, Kylan Boswell.

Yesterday's board

10 games, the model went 6-4. The market favourite went 6-4.

Where the model and the market split: CHA at WSH: the model took CHA (51%), the market WSH; the served pick was WSH and the pick hit. DEN over PHX: model 51%, market 62%, a 10-point gap; the pick hit. HOU over DAL: model 60%, market 68%, an 8-point gap; the pick missed. BOS over CHI: model 81%, market 86%, a 5-point gap; the pick hit.

The firmest calls: BOS 85% over CHI (hit), DET 73% over BKN (hit), MIA 72% over IND (hit).

The Model Card is a different question from the pick: the pick is the more likely winner, the card leg is the side whose price beats the model's own number. The card went 5-2 on its 7 legs here.

Season to date through October 30: 55-28 (66.3%), Brier 0.205; market favourites 53-28 on the 81 with a line; picks at 60% or better are 39-13.

The record

Graded regular-season picks since 2025-10-31: 55 of 83 (66.3%), Brier score 0.205. The live figure, the hit rate by confidence band and every voided pick with its reason are on the NBA accuracy page.

Responsible play

This is model output, not betting advice. Verdexed publishes its model's probabilities and edges for informational and entertainment purposes only. Nothing here is a recommendation to place a wager, and no outcome is guaranteed, even the model's highest-confidence picks lose regularly.

You must be of legal betting age in your jurisdiction and located where sports wagering is legal to bet. Sports betting is not available everywhere; know and follow the laws where you are. Never bet more than you can afford to lose, and never chase losses.

If gambling is affecting you or someone you know, help is available. In the US, call or text 1-800-GAMBLER (1-800-426-2537), or visit ncpgambling.org. Please play responsibly.