Game Predictions | March Madness 2022

The table below provides our predictions for all games in the 2022 NCAA Tournament. The table will be updated after each round of the tournament, with new games/predictions added as they become available. A brief description of how to interpret the predictions is provided above the table, and a summary of the historical accuracy of each model is provided at the end of the post. See our related posts on our Full 2022 Tournament Bracket and our Tournament Simulation results.

Win Probability & Spread Predictions

Win Probabilities – For each game, “Team1 Win Prob” represents our model’s probability that Team1 (the better-seeded team) wins the game. Probabilities below 50 indicate that Team2 is more likely to win the game.

Spreads – The “284 Spread” is our model’s prediction of how many points Team1 will win by. For both Vegas and 284 Spreads, negative values indicate Team1 is favored, while positives indicate Team2 is favored.

Totals – The Vegas Total can be compared to our “284 Tot,” which is our model’s prediction of how many points will be scored in the game.

Team1Team2RoundTeam1
Win Prob
Vegas
Spread
284
Spread
Vegas
Tot
284
Tot
1 Kansas8 UNC60.67-4-4.2153149.2
1 Kansas2 Villanova50.69-4.5-3.1132.5138.1
2 Duke8 UNC50.62-4.5-2.2151153.9
1 Kansas10 Miami40.76-6-7.0147146.6
8 UNC15 St. Peter's40.68-8-7.1137135.9
2 Duke4 Arkansas40.75-4-5.7146146.8
2 Villanova5 Houston40.60+2-2.1128.5131.4
3 Purdue15 St. Peter's30.80-12.5-13.6135.5134.0
1 Kansas4 Providence30.84-7.5-10.4141.5141.5
4 UCLA8 UNC30.69-2-5.7142.5141.1
10 Miami11 Iowa St30.56-1.5-0.9133.4136.9
1 Gonzaga4 Arkansas30.88-8.5-14.3154.5157.4
2 Villanova11 Michigan30.70-4.5-4.7135.5134.2
2 Duke3 Texas Tech30.72+1-3.5135.5139.4
1 Arizona5 Houston30.68-2-2.5145144.7
4 Illinois5 Houston20.54+4.5+0.4133136.0
2 Villanova7 Ohio St20.75-5.5-6.7132.5131.5
2 Duke7 Michigan St20.75-6.5-7.3144.5143.8
3 Wisconsin11 Iowa St20.60-4.5-2.7125.5131.5
3 Texas Tech11 Notre Dame20.78-7.5-8.8133135.1
2 Auburn10 Miami20.71-7.5-6.8144.5142.7
3 Purdue6 Texas20.72-3-5.1134137.3
1 Arizona9 TCU20.87-9.5-10.4143143.4
1 Baylor8 UNC20.69-5.5-6.6149143.6
1 Kansas9 Creighton20.81-11-10.0138.5143.6
3 Tennessee11 Michigan20.69-5.5-4.5136137.0
4 Providence12 Richmond20.62-3-1.7134134.9
4 UCLA5 St. Mary's20.70-2.5-4.5126.5128.9
7 Murray St15 St. Peter's20.78-8-7.7130131.7
4 Arkansas12 New Mex St20.68-6.5-5.4139136.5
1 Gonzaga9 Memphis20.83-10.5-13.0154.5156.5
7 Ohio St10 Loyola Chi10.59-1-1.4132.5134.4
2 Auburn15 Jax St10.83-15.5-13.0138.5137.5
3 Texas Tech14 Montana St10.84-15-13.2131.5134.2
3 Purdue14 Yale10.90-16-18.8143141.9
2 Villanova15 Delaware10.87-15.5-14.6133.5135.4
7 USC10 Miami10.74-1.5-4.7139.5139.1
6 Alabama11 Notre Dame10.65-4-5.0152.5148.2
6 Texas11 VA Tech10.67-1-4.1124.5128.0
4 Illinois13 Chattano10.81-7.5-11.6135.5134.9
2 Duke15 CS Fullerton10.91-18.5-18.5145.5145.5
6 LSU11 Iowa St10.73-4-4.6127.5137.1
1 Arizona16 Wright St10.90-22-15.0156150.6
5 Houston12 UAB10.83-8.5-10.9136138.1
7 Michigan St10 Davidson10.64-1.5-2.4140137.7
3 Wisconsin14 Colgate10.67-7.5-4.3139138.5
8 Seton Hall9 TCU10.71-0.5-3.1129.5134.1
6 Colo St11 Michigan10.50+2.5+2.9139138.7
4 Providence13 S Dakota St10.57-2-0.9149.5143.9
8 Boise St9 Memphis10.60+2.5+1.3133.5134.8
1 Baylor16 Norfolk St10.89-20.5-17.8137.5140.3
3 Tennessee14 Longwood10.88-17.5-13.5132136.9
5 Iowa12 Richmond10.79-10.5-7.7151146.0
1 Gonzaga16 Georgia St10.91-23.5-24.8148150.6
8 UNC9 Marquette10.77-3-5.8151.5148.7
5 UConn12 New Mex St10.77-7-6.5131.5130.4
2 Kentucky15 St. Peter's10.86-18-12.5131.5134.2
5 St. Mary's12 Indiana10.64-2-3.0126.5130.1
8 SDSU9 Creighton10.66-2.5-3.3120131.0
4 Arkansas13 Vermont10.59-5-2.2139136.4
7 Murray St10 San Fran10.69-1-2.8136.5140.0
4 UCLA13 Akron10.82-13.5-13.8127.5132.8
1 Kansas16 Texas So10.91-21.5-18.2144.5143.6
16 Texas So16 TX AM CC00.65-3.5-3.4134.5142.3
12 Wyoming12 Indiana00.43+4+3.8132135.1
16 Wright St16 Bryant00.72-3.5-4.8154.5149.0
11 Rutgers11 Notre Dame00.52+1+1.2131.5134.2

Model Accuracy

Below is a summary of how each individual model performed on all 2017-2021 tournament games, with 2022 results being added to the tables as they become available. Note that spread/cover and total/over models are graded against the numbers as they are shown in the tables above. Additionally, links to detailed recaps of all predictions from previous tournaments can be found by following links in the header menu above.

Year Win Prob 284 Spread 284 Total
Rec % Rec % Rec %
2017 47-15 0.76 34-26 0.57 39-22 0.64
2018 44-19 0.70 32-28 0.53 38-25 0.60
2019 45-18 0.71 24-36 0.40 32-29 0.52
2020
2021* 43-20 0.68 33-27 0.55 36-22 0.62
2022* 46-21 0.69 32-34 0.49 41-24 0.63
Total 225-93 0.71 155-151 0.51 186-122 0.60

* Note that we have modeled the 2021 and 2022 tournaments using a different data/methodology than in previous years due to the various irregularities caused by COVID this season. Applying the historical data/methodology would have been a bit of a “square peg round hole” situation due to these irregularities. So, we decided to model the 2021 and 2022 tournaments with a clean slate, using data only from the 2021 and 2022 seasons, individually, to generate our models/predictions. Additionally, note that we no longer produce the Cover Probability and Over Probability models, so the “284 Spread” and “284 Total” will be our main focus for spreads and totals moving forward.