Decision Making by Applying Machine Learning Techniques to Mitigate Spam SMS Attacks

Due to exponential developments in communication networks and computer technologies, spammers have more options and tools to deliver their spam SMS attacks. This makes spam mitigation seen as one of the most active research areas in recent years. Spams also affect people’s privacy and cause revenue loss. Thus, tools for making accurate decisions about whether spam or not are needed. In this paper, a spam mitigation model is proposed to find spam from non-spam and the different processes used to mitigate spam SMS attacks. Also, anti-spam measures are applied to classify spam with the aim to have high classification accuracy performance using different classification methods. This paper seeks to apply the most appropriate machine learning (ML) techniques using decision-making paradigms to produce a ML model for mitigating spam attacks. The proposed model combines ML techniques and the Delphi method along with Agile to formulate the solution model. Also, three ML classifiers were used to cluster the dataset, which are Naive Bayes, Random Forests, and Support Vector Machine. These ML techniques are renowned as easy to apply, efficient and more accurate in comparison with other classifiers. The findings indicated that the number of clusters combined with the number of attributes has revealed a significant influence on the classification accuracy performance.