Algorithm 1: Multi-Objective Multi-Instance Learning (MOMIL)

Inputs:  S: single-instace data $S=\{(x_1,y_1),(x_2,y_2),\dots .,(x_{n\ast m},y_{n\ast m})\}$  T: test set containing b bags  m: the number of players in a team  n: the number of bags in the training set Outputs:  Y: predicted class labels on given query bags Begin: for:$i=1$tondo