Spam is unsolicited email advertising for products and services delivered to a receiver. Spam comes in a variety of forms. More than 500 million spam messages in English are sent every day, according to the WHOIS database. I gather spam datasets from websites for this project. In this paper, I've provided the project's midterm update.

I detect spam messages on websites first. In order to achieve this, I looked up the official websites to determine the relevant ones I would focus on before collecting the spam datasets from the websites. I then utilize Python tools like NumPy and Matplotlib, which are well-known in the domains of data analysis and visualization, to analyze and visualize the dataset. Before performing any data analysis, I divided the dataset into training and testing sets. I do this so the machine can figure out how to recognize spam communications before displaying any results to human users for testing purposes. After models have been improved using fresh training sets, testing sets assess how successfully they have been taught (a process known as hyperparameter optimization).

To the literature review as well. The research reveals that there has been a marked increase in the volume of unwanted email messages sent across computer networks since 2007, particularly since Google's Panda update in its search engine results in pages in 2010. (SERP). Since 2007, there has also been an upsurge in harmful software, making spammers' operations more effective. In order to prevent unsolicited commercial email messages from being sent over computer networks either knowingly or unknowingly by cybercriminals themselves or their unwitting proxies acting on their behalf, it is crucial to develop software solutions that will help combat this cybercrime problem effectively. This will allow future online users to enjoy free and legitimate access to information without being subjected to it.