ACCURATE SPAM DETECTION USING SUPERVISED MACHINE LEARNING TECHNIQUES

A data transmission network consisting of millions of sensors and actuators that are connected through wired or wireless channels. In the past ten years, it has grown very quickly, and by 2020, it is expected that more than 25 billion devices will be linked together. Coming years will see a huge increase in the amount of data that these gadgets produce. In addition, the gadget generates a large amount of data in a number of different formats. A network made up of millions of sensors and actuators that are linked together by wired or wireless pathways so that data can be sent and received. It is expected that by 2020, there will be more than 25 billion connected gadgets. This shows how quickly things have grown over the past ten years. Over the next few years, these gadgets will show an increasing amount of data. The gadget creates a lot of data in a number of ways. The quality of this data relies on how often and where it is collected. In this situation, machine learning techniques are very important for improving biotechnology security and permission, as well as for finding oddities to make things safer and easier to use. On the other hand, attackers often use learning techniques to take advantage of weaknesses in systems. To make gadgets safer, we recommend using machine learning to find malware on them. For this, you should use the Machine Learning Framework for Spam Detection. This system tests four machine learning models using various measures and sets of input features. Based on the changed input values, each model comes up with a spam score. This score, which is based on a number of factors, shows how reliable the device is. The results show that the suggested method is better than the other choices.