Comparison of Classification Algorithms Like Neural Network (NN), Support Vector Machine (SVM), and Naïve Theorem (NB) and Back Propagation TECHNIQUE for Automatic Email Classification

Abstract

This paper proposes a replacement email classification model using a supervised technique of multi-layer neural network to implement back propagation technique. Backpropagation adjusts the loads in Associate in Nursing quantity proportional to the error for the given unit (hidden or output) increased by the weight and its input. The coaching method continues till some termination criterion, like a predefined mean-squared error, or a most range of interations. Email has become one altogether the fastest and therefore the best styles of communication. However, the increase of email users with high volume of email messages might result in un-structured mail boxes, email congestion, email overload, unprioritised email messages, and resulted at intervals the dramatic increase of email classification management tools throughout the past few years. Our aim is to the use of empirical Analysis to select out Associate in Nursing optimum, novel assortment of choices of a users’ email contents that modify the speedy detection of the foremost important words, phrases in emails.