Naive Bayes is based on probability fundamentals. The probability of a single event occurring (the observational probability) is calculated by taking the number of times the event occurred and dividing it by the total number of processes that could have led to that event. For example, a call center receives over 100 support calls per day, 50 times over the course of a month. You want to know the probability that a call is responded to in under 3 minutes based on the previous times it was responded to. If the call center manages to match this time record on 27 occasions, then the observational probability of 100 calls being answered in under 3 minutes is as follows:

P(100 support calls in under 3 mins) = (27 / 50) = 0.54 (54%)

100 calls can be responded to in under 3 minutes in about half the time, based on records of the 50 times it occurred in the past.