Recent Changes
- NEW! 2019 Apr 26: Published preseason Canadian Premier League "forecast." Given that the forecast has no data about the teams, it is currently pure chance, but will begin being informed by results as matches are played.
Canadian Soccer 2019 Forecast
This system is an attempt to model the Canadian Premier League season, and provides useful insight into the probability of various occurrences in the remainder of the season.
The algorithm projects the results of future matches by simulating them. No data about the teams prior to 2019 is used. The model uses various assumptions in the absence of previous data:
- Goals per match will be similar to the average between Major League Soccer and Iceland's top division (Úrvalsdeild).
- Home-field advantage will be similar to Major League Soccer, thought to be a better parallel to the CanPL because of travel. (Iceland's home field advantage is significantly smaller.)
- Parity will be similar to Iceland's Úrvalsdeild, thought to be a better parallel to the CanPL because it is a club-based system, rather than a franchise-based system like Major League Soccer.
The algorithm results in a reasonable model for wins, losses, and draws. The actual schedule is used, and each match is simulated individually. The season is simulated a number of times (currently 100,000), and the results of the simulations are tallied and presented.
Tiebreakers
The algorithm uses the first three tiebreakers correctly:
- Wins
- Goal differential
- Goals scored
Canadian Premier League Championship
Sources differ on the format of this competition; some say the format has not been decided, while others say it will be a two-legged home-and-away series. The forecast currently assumes it will be a home-and-away series, and randomly chooses which of the two qualifying teams hosts the first match.
Power Rankings
The power rankings algorithm uses 2019 matches (only), along with mean-regression estimates derived from Iceland's top division (Úrvalsdeild), in order to estimate the offensive and defensive strength of each team. These measures are aggregated into a single power ranking.
The power rankings correspond to the relative frequency with which each team should score a goal against each other team. As such, they represent the probability that a team would win against other teams in a golden goal situation. High-scoring teams will tend to have more wins (and losses), and fewer ties. For this reason, given two teams with the same power ranking, the higher-scoring team should perform better in the standings.
Future work
- Add individual team pages
- Add contigent probabilities based on outcome of team's next match
- Implement further tiebreakers for Canadian Premier League
- Add forecast for the Canadian Championship
- Add forecast for CONCACAF League qualifying (FC Edmonton, Forge FC, Valour FC; see explanation).