The forecasts of this weekend’s fixtures throw up some curious comparisons between the Model and those implied by the average of online bookmaker odds. These potentially suggest behavioural biases in how either the bookmakers or their customers form expectations. Here are a few examples:

  1. Man City vs Man Utd: The Model is more favourable towards Utd than the odds setters, giving them a 14% chance of a win compared with 10% for the latter. City are expected to score 2.1 goals, compared with 0.9 for Utd. The Model says that the most likely outcome is 2-0 (11%). Reverse favourite-longshot bias?
  2. Watford vs Crystal Palace: Based on recent form, the Model makes Palace marginal favourites, with a 41% chance of a win. But the bookmakers somehow think Watford are more likely to win, giving Palace just a 32% chance of victory. The Model says the most likely outcome is 1-1 (11%) though. Home bias?
  3. West Ham vs Arsenal: The Model makes West Ham marginal favourites, at 39%. The Bookmakers however make Arsenal strong favourites, at 49% for the win. Big team bias?

The table below gives the rest of the Model’s forecasts for Round 16 of the Premier League, along with forecast probabilities estimated from current online bookmaker odds.

EPL forecasts R16 2019, RED
  • Expected Goals: the forecast average number of goals the Model expects for Home and Away teams
  • Outcome Probs: the model predicted % chance of either a Home or Away win, with 100 minus these two numbers being the % chance of a draw.
  • Score Picks: the Most likely forecast scoreline outcome, as well as the most likely conditional on the most likely result outcome happening.
  • Home wins / Draws / Away wins: the predicted % chance of various potential scoreline outcomes of the match.
  • Mean odds: Estimates of online bookmakers’ average probabbility forecasts for the Home and Away teams to win, which could be compared with Outcome Probs.