Algorithm 3 Pseudocode of imbalanced metric-driven models based on AWE.

Input: S: new data chunk

C: ensemble of classifiers

K: size of the ensemble

Output: C: ensemble of classifiers with updated weights

X ← sampled S

Train new classifier $C^{\prime }$ on X;

Estimate weight of $C^{\prime }$ with cross-validation on S based on (5), (6) or (7);

for $C_i$ in C do

Calculate weight $w_i$ of $C_i$ on S based on (5), (6) or (7);

end for

C ← K classifiers with the highest weights from $C\cup C^{\prime }$;

for $C_i$ in C do

$w_i\leftarrow \frac{w_i}{{\sum }_{C_{i}inC\cup C^{\prime }}{w}_i}$

end for

return C;