Abstract
Due to the massive proliferation of Short Message Service (SMS), Spammers got the interest to dig their way into it in the hope to reach more targets. Spam SMS can trick mobile users into giving away their confidential information which can result in severe consequences. The seriousness of this problem has raised the need to develop an accurate Spam filtration solution. Machine learning algorithms have emerged as a great tool to classify data into labels. This description fits our case perfectly as it classifies SMS into two labels: spam or ham. This paper will tackle the SMS spam filtration solutions by introducing a hybrid system using two types of machine learning techniques: supervised & unsupervised machine learning algorithms. The new hybrid system is designed to achieve better spam filtration accuracy and F-measures