260
F. Firouzi et al.
Original Dataset
Training Set
Test Set
Training Set
Validation Set
Test Set
Training and creating
machine learning model
Evaluating the trained
model using unseen data
Fig. 5.13 Hold-out technique: splitting the dataset into training and test set
Fig. 5.14 Threefold
cross-validation
Test
Train
Train
Train
Test
Train
Train
Train
Test
Iteration 1
Iteration 2
Iteration 3
Original Dataset
model can perform on unseen data. Figure 5.13 demonstrates the underlying
concepts related to these datasets.
(b) K-fold Cross-validation: In this technique, the original dataset is repeatedly
and randomly split into “k” equal-sized folds (also called groups, buckets,
or sections). For each unique group, we take it as the test (hold-out) dataset
and the other groups as the training set. This process is iteratively done for k
times until each fold of k folds have been used as the test set (see Fig. 5.14).
5.2 Regression Analysis
Regression analysis is a subcategory of supervised machine learning. It is used to
study the correlation between a dependent (usually called target or output) and an
independent variable (called predictor or features or input). In this machine learning