NBA • Tracking

Model Performance

This page tracks Dr Cover's NBA Model – Version 1. The model was built using machine learning and decades of historical NBA data to evaluate performance over time. This is the baseline release, and future versions will include additional enhancements, expanded features, and continued calibration as the OddsRX platform evolves.

📄 Read: NBA Model Notes

Data: Live
Last updated: 5/16/2026, 11:44 PM
Rows: 44

Sides (Winners)

Split Games Correct Accuracy
Overall 1,208 762 63.1%
Pred not B2B 1,059 671 63.4%
Mkt agree 862 618 71.7%
Conf 50–55% 817 470 57.5%
Book fav (>55%) 809 591 73.1%
Home picks 763 498 65.3%
Away picks 445 264 59.3%
Conf 56–65% 384 286 74.5%
Mkt disagree 309 120 38.8%
Dog (<45%) 216 70 32.4%
Pred on B2B 149 91 61.1%
Conf 66–75% 6 5 83.3%
Conf >75% 1 1 100.0%

Spreads (ATS)

Split Games Correct Accuracy
Overall 1,179 605 51.3%
Picking dog 1,045 533 51.0%
Pick not B2B 1,009 508 50.3%
WinConf 50–55% 795 418 52.6%
Disagrees w/ winner 728 367 50.4%
Away picks 636 313 49.2%
Home picks 543 292 53.8%
Spread >7.5 468 233 49.8%
Agrees w/ winner 451 238 52.8%
WinConf 56–65% 378 182 48.1%
Spread 4–7.5 361 183 50.7%
Spread ≤3.5 350 189 54.0%
Pick on B2B 170 97 57.1%
Picking favorite 134 72 53.7%
WinConf 66–75% 5 4 80.0%
WinConf >75% 1 1 100.0%

Expected Value

Split Games Correct Accuracy
Negative EV 836 600 71.8%
Positive EV 339 139 41.0%
EV >5% 292 114 39.0%
EV >10% 264 96 36.4%
EV >15% 237 84 35.4%
EV >20% 210 72 34.3%

Totals (O/U)

Split Games Correct Accuracy
Overall 1,176 582 49.5%
Pred overs 628 294 46.8%
Pred unders 516 258 50.0%
Overs Δ≥5 363 165 45.5%
Unders Δ≤-5 249 123 49.4%

Variance / Pace

Split Games Correct Accuracy
Low SD ≤25.6 593 281 47.4%
Slow ≤98.3 592 293 49.5%
Fast >98.3 584 289 49.5%
High SD >25.6 583 301 51.6%