Algorithm 1. Feature organization.

1: Initialize a train dataset ${\mathcal{D}}_{train}\leftarrow \varnothing$

2:   For t = p to n

3:       Input data $X=\left\{x_{t-p+1},x_{t-p+2},\cdots ,x_{t-1},x_t\right\};$

4:           $Y_{his,i}=\left\{y_{t-p+1},y_{t-p+2},\cdots ,y_{t-1}\right\},Y_{t,i};$

5:           $Z=\left\{z_{t-p+1},z_{t-p+2},\cdots ,z_{t-1},x_t\right\};$

6:           $Q=\left[X,Y_{his,i},Z\right];$

7:          Insert (Q, $Y_{t,i}$) into ${\mathcal{D}}_{train};$

8:   End