Generally, predicted label is positive when the score $s > 0.5$. It’s reasonable when $num_pos:num_neg = 1: 1$. However, the score should be adjust with the change of ratio between the number of positive and negtive samples.

We define $m^+$ is the number of positive samples, and $m^-$ is the number of negtive samples. The decision rule should be satified with
$$frac{s}{1-s}=frac{m^+}{m^-}$$ In implementation, we choose the optimal threshold by ROC curve.

对于 extremely class imbalance 的问题, 比较有效的处理方法包括重采样, meta-learning et.al..