Objective: We set out to see if we could use each player's average PB score this season and the variability in their scores combined with the fixture data to estimate each player's Performance Buzz dividends so far this season.
We used this data to simulate each gameday so far this season 100 times and recorded the winners of each game day every time. We then aggregated these results to find each player's average dividend. This is the model's expectations as to how much each player would have paid out in dividends so far in the games they've played this season in which they were eligible to win Performance Buzz.
This is useful to help identify the players who have been lucky to win a performance buzz so far this season (perhaps he happened to have his best day on a day others flopped). On the flip side, it will help identify the player's who have yet to win as much as their performance buzz scores so far deserve.
We recommend using the filter to view each position individually.
We plan to further enhance this model to account for the difficulty of each game and whether the player is playing at home. We will be releasing future predictions based on this model shortly.
Please note the expected payouts do not account for the change to double dividends from November 1st so it may be slightly reduced for those players who were likely to win on the November gamedays.
It is also worth noting that this is based on the level of competition each player faced in the games so far so defenders, for example, will have a much larger expected payout for the last couple of months than they will in future projections.