Some clarifications about the project

[AntonioGiovanniSchiavone]

Hi @uPeppe ,

I've read your article on Medium and I have a few questions:

• Did you use the project for both Fantacalcio Classic and Mantra?
• For the Mantra version, how did you handle players with multiple roles and select the best formation among the various available modules for each matchday?
• Did you apply the sin-arcsinh probability distribution to goalkeepers as well?
• Which bonuses and penalties did you consider? (e.g., goalkeeper clean sheets, defense modifier)
• For each matchday, did you consider validating the results by calculating the delta compared to the actual best formation?

Thanks!

[uPeppe]

• Yes, even though only "normal" role (P-D-C-A) is considered as a feature
• Let's say I'd choose the lineup manually, depending on the players expected votes. There is no code for selecting automatically the optimal lineup through optimization method. However, simulate_lineup contains code for calculating the expected points of an input lineup (which is treated as a probability distribution itself) and could potentially be extended to try multiple lineups.
• Yes, and for fantavote it results on a distribution skewed to the left (due to the -1 penalty for each goal)
• For goalkeepers, only goals -1 and cards if I remember correctly. Clean sheet probability is treated as an additional output, other than vote and fantavote. Defense modifier is not an output for the player prediction, but is taken into account in lineup_simulation as it depends on multiple players. Clean sheet bonus is treated there as well, as not all leagues use that.
• Not really in a methodic way. Could be an idea.