FINAL: Merrimack 54 — Siena 64. Our Monte Carlo simulation projected Merrimack 76.3 - Siena 77.0 (Siena at 60.2% win probability). The spread is -1.5 and the total is 128.0.
Merrimack
76.3
Projected Score
VS
O/U 128.0
Siena
77.0
Projected Score
Win Probability
MerrimackSiena
-1.5
Spread (Merrimack)
128.0
Total Line
10,000
Simulations
Calibrated accuracy at this confidence: 63.5% (4,284 games)
Projected Points Range 10th – 90th percentile
Siena
647790
Merrimack
647689
Projected
Merrimack 76.3 — Siena 77.0
Actual
Merrimack 54 — Siena 64
Pick Results
Over 127.5totalLOSS-0.50u
Spread Analysis
Merrimack Cover
39.2%
Siena Cover
60.8%
ATS Edge: -3.8 pts
AI Intelligence Analysis
LEAN -1YELLOW ZONE50.1% WR (n=7215)
A 22-point total edge (149.5 model vs 127.5 market) and model flipping the winner (Siena away underdog at 57.8% vs Merrimack home -3) both suggest potential data integrity issues — totals overs are 1-3 over 14 days and the model's 80%+ predicted probabilities have only 25% actual WR; this game should be observed, not wagered.
Key Factors
- Total edge: Model predicts 149.5 vs market 127.5 — +22pt gap triggers DATA_INTEGRITY flag
- Model winner: Siena 57.8% (away underdog) while Merrimack is -3 home favorite — model contradicts market direction
- 14-day overs record: 1W-3L (25.0%, -3.09u) — worst performing market in current window
- High-edge total zone (25%+): 41.7% WR historically — no bet on over is warranted
- No ML odds available from The Odds API for this game — limited market intelligence
Risk Factors
- Model's total prediction (149.5) is 22 points above market (127.5) — extreme outlier requiring DATA_INTEGRITY flag
- Model predicts Siena wins (-1.9 margin) while market has Merrimack -3 — major directional conflict
- No ML odds available to evaluate moneyline value
HIGH EDGE WARNINGTOTALS VALUEMODEL MARKET CONFLICTDATA INTEGRITY
Edge Analysis
Moneyline
Siena 60.2%
--
Spread
-1.5
--
Total
128.0
--
How this prediction was generated: This page shows output from the Olympus Bets College Basketball Monte Carlo engine. Each game is simulated 10,000 times using real-time team data, injury reports, and current odds. Probabilities are calibrated using Bayesian methods and sized via the Kelly Criterion. Full methodology →