How to read a prediction

Every game on iPick Sport carries the same few numbers. This page says what each of them means, and what it does not.

The pick and its probability

The pick is the team the model gives the better chance of winning. The percentage beside it is that chance: 57% means that, out of 100 games like this one, the model expects the pick to win about 57 — and to lose about 43.

The two teams' percentages add up to 100. A game at 51% and 49% has a pick too, and it is close to a coin flip.

Pick strength

The label under a probability is a name for it, not a second opinion:

  • Coin flip: under 55%.
  • Slight: 55% to 60%.
  • Moderate: 60% to 70%.
  • Strong: 70% to 80%.
  • Very strong: 80% or more.

Reliability

Reliability says how far that probability deserves to be believed for this one game: High from 70%, Medium from 55%, Low under that. It does not say how likely the pick is to win. A 66% pick with low reliability is a 66% the model itself has reasons to doubt.

What it is made of is on its own page: How reliability is measured.

The probability range

The range — 52% to 62%, say — is where the model puts the pick's real chance once its own past misses are counted. It is wider when few past games stand behind that probability, when the model has been off at that level, and when outside estimates of the same game are far from the model's.

Expected margin and expected total

A second model estimates by how much the winner wins, and how many runs, points or goals the two teams score between them. “ATL by 0.8 ± 4.5” reads: on average Atlanta wins by 0.8, and that estimate has typically been off by about 4.5 in past games.

In baseball and hockey a margin under one run or goal is usual. It is an average over many games like this one, not a score.

While a game is played, and after

  • Live: while a game is being played, the percentage shown is ESPN's live win probability. What the model said before the game is kept in the game's own view, as “Before the game”.
  • Final: the score, and a green tick when the pick won or a red cross when it lost.
  • Retro: a prediction computed after the game from what was known before it. It is marked, and counted apart from the ones made before the game.

The Picks page

Picks lists the day's picks most likely to be right. Its percentage is the model's probability weighed against outside estimates of the same game, so it can be lower than the one on Predictions, and now and then the side is the other one.

What none of it is

A probability is an estimate, not a promise, and none of this is advice: see the Terms of Use. How the numbers are made is in What each model knows.