“…Despite its simplicity, NB classifier is one of the powerful classification techniques. Due to its easiness, along with its good performance, NB is widely used to address classification problems in several real-world applications [ 28 , 32 ]. NB has been chosen to be implemented in CP for the following reasons; (i) it can provide fast predictions rather than other classification algorithms because the training time has an order O(N) with the dataset, (ii) NB can be easily trained with small amount of input training dataset and it can be used also for large datasets as well, (iii) NB is easy to be implemented with the ability of real-time training for new items, (iv) it has no required adjusting parameter or domain knowledge, (v) NB is less sensitive to missing data, (vi) it has high capability to handle the noise in the dataset, (vii) NB is Incremental learning algorithm because NB functions work from approximation of low-order probabilities which are extracted from the training data [ 33 , 34 , 35 ].…”