2.3. Validation of the model
A k-fold cross validation [6] was carried out in order to test the TAN, as well as the 3 other models. This technique randomly splits the dataset into k subsets and the method is repeated k times. In each step, one subset is used to test the model built from the remaining k-1 subsets (training subset). Then, the RMSE (Eq. 4) is computed in each step. Finally, the mean of the RMSE is computed to measure the accuracy of the model. In this work, a k-value of 5 was applied.