Simple Explanation of Naive Bayes Algorithm

                     Naive Bayes algorithm  generally assumes that the input features are independent to each other.It gives the amount of probability of one feature given the amount of  another feature.It is a type of classification algorithm.

The formula is:

      

   where

     P(A|B)= Posterior probability - means probability of feature A given the                                                            probability of B

    P(B|A) =Likelihood - means probability of feature B given the                                                             probability of A

     P(A) = Prior Probability - means probability of the feature A

     P(B) = Predictor Probability -means probability of the feature B

Here, | represents conditional probability.

For example : Polio has been rare these days.For Instance, let’s assume the there is 1% chance of patients getting polio.Also, assume , 99%  the test results are accurate.

a.  a. Probability tree

b.Reverse tree

 The True Positive of the main tree implies that there is 50% chance that the Patient can have Polio given that the test result is positive and similarly, for the True Negative.

Hope, this simple example gave you a glimpse of how the naive bayes algorithm works.

Please like,comment and share if you hope this is useful.

Signup and start your first crypto investment here : Binance