Spam detection or anti-spam techniques are methods to identify and filter out unwanted, unsolicited, or malicious emails, commonly known as spam. These techniques aim to enhance email security, reduce the risk of phishing attacks, and improve the overall user experience. The prediction of spam emails falls under the broader email filtering or classification category. Specifically, it is a part of the field of machine learning and data mining, where techniques are employed to automatically categorize emails into different classes, such as "spam" or "non-spam" (ham). This process involves using various algorithms and features to analyze emails' content, structure, and metadata to determine whether they will likely be spam or legitimate messages. Our objective is to use Machine Learning to predict and identify simplistically whether the Email is Spam Or Not. It was concluded and considered that the two datasets we can use have many Machine Learning algorithms. The proposed algorithms were tested: k-nearest Neighbor, Gradient Boosting, Random Forest, Naïve Bayes, Decision Tree, and Logistic Regression. After rigorous testing, the only algorithm, Gradiant boosting, stayed dominant in most of the testing, achieving accuracies of 98.5%; also, the other dataset with the best algorithm was Gradiant boosting, which scored the highest accuracy in all the testing, which was 98.6%. As shown in this paper, Machine Learning algorithms, such as supervised or unsupervised models, are trained on datasets containing examples of both spam and legitimate emails. These models then use the learned patterns to classify incoming emails. Can adapt to new spam patterns, effectively handling complex relationships in data.