Content Based Classification using Clustering Algorithm

This survey paper categorizes, compares, and summaries from some published technical and review articles in automated fraud detection within the last few year. Short Message Service (SMS) has become one of the most common communication method due to fast increment in the number of users worldwide. As usage of SMS increased spam messages also increased. To filter spam SMS there are many methods available like Support vector machine(SVM), Naive Bayesian, K-nearest neighbor(KNN), K-star, Feature extraction, Feature selection, Tokenizer etc. Naive Bayesian is considered as one of the most effectual and significant learning algorithm for machine learning and data mining and also has been treated as a core technique in information retrieval. Feature extraction is the best method for SMS spam filtering. K-nearest neighbor algorithm is simple to understand but non parametric lazy learning algorithm. Support vector machine is the feature based classifier and it has high accuracy.