How does a computer pick MLB games?

The model builds power ratings from team efficiency, simulates each matchup thousands of times to produce a projected run line and total, then compares that projection to the sportsbook line. When the gap is large enough, the game becomes a pick.

How often are the picks updated?

Picks post each morning when the day's lines open and refresh as starting pitchers are confirmed and the market moves, right up to first pitch.

How Our MLB Computer Picks Work

Q: Are computer MLB picks profitable?

A model only adds value if it beats the closing line often enough to overcome the sportsbook's vig — roughly a 52.4% win rate at -110. A disciplined model targeting positive expected value can clear that bar over a full season, but no system wins every week.

No touts. No gut calls. Every pick on this site comes from the same repeatable process — here's exactly what the model does, in plain English.

1. Power ratings from what teams actually do

The foundation is a set of power ratings — a single number, measured in runs, for each team representing its true strength on a neutral field. Rather than lean on win-loss records (which hide how a team won), we build ratings from run-scoring and run-prevention efficiency, park-adjusted and opponent-adjusted. Ratings update every day as new games come in, and they decay old performances so an April hot streak doesn't dominate a July projection.

2. Adjust for the matchup

Two equal teams don't play equal games — and in baseball, the single biggest daily swing is the starting pitcher. Before projecting, the model layers on context: home-field advantage, the ballpark's run environment (a game in Coors Field plays nothing like one in a pitcher's park), bullpen strength, and weather — wind and temperature meaningfully move a total for outdoor parks.

3. Simulate the game thousands of times

With ratings and adjustments set, the model simulates each matchup thousands of times. Every simulation produces a final run total for each side; run enough of them and you get a distribution — the model's projected run line, projected total, and a win probability for each team.

The output isn't "Team A wins." It's "Team A wins by 2+ in 41% of simulations." Probabilities, not certainties.

4. Compare to the market — and only bet the gap

This is the step that matters. Sportsbook lines are sharp; beating them is the entire game. The model compares its projected numbers to the live market. If we project a team as a clear favorite but the moneyline or run line is priced softer than our number, that gap becomes a pick. Small gaps are noise and get filtered out. The size of the gap sets the confidence score and whether a play is labeled a Lean or a Strong play.

5. Grade everything, publicly

Every pick is locked against the line at post time and graded win/loss/push on the results page. The all-time record is the honest scoreboard for whether the model is actually adding value.

Frequently asked questions

Are computer MLB picks profitable?

Only if the model beats the closing line often enough to overcome the vig — about a 52.4% win rate at standard -110 juice. A disciplined, positive-expected-value approach can clear that over a full season, but variance is real and no system avoids losing weeks.

Is this the same as "AI picks"?

The engine is a statistical simulation model. "AI" and "computer picks" are marketing shorthand for the same idea: a systematic, data-driven process instead of a human hunch.

Can I just bet every pick blindly?

You can, but sizing by confidence and shopping for the best number will meaningfully improve your results. See our guide to using the picks.

How our MLB computer picks work