This paper provides a comprehensive overview of classification assessment methods, focusing on binary and multi-class classification problems. It introduces key metrics such as accuracy, sensitivity, specificity, precision, recall, F-measure, and others, and discusses their sensitivity to imbalanced data. The paper also presents graphical methods like the Receiver Operating Characteristics (ROC) curve, Precision-Recall (PR) curve, and Detection Error Trade-off (DET) curve. The ROC curve is explained in detail, including how it is generated and interpreted, with an emphasis on the Area Under the Curve (AUC) metric. The PR curve is also discussed, highlighting its use in evaluating classification performance, especially in imbalanced datasets. The paper includes illustrative examples to demonstrate how these metrics are calculated and how they behave under different data conditions. It also addresses the robustness of these metrics against imbalanced data and provides a step-by-step approach for plotting ROC, PR, and DET curves. The paper concludes with a discussion on the relationships between different assessment methods and their applications in real-world scenarios.This paper provides a comprehensive overview of classification assessment methods, focusing on binary and multi-class classification problems. It introduces key metrics such as accuracy, sensitivity, specificity, precision, recall, F-measure, and others, and discusses their sensitivity to imbalanced data. The paper also presents graphical methods like the Receiver Operating Characteristics (ROC) curve, Precision-Recall (PR) curve, and Detection Error Trade-off (DET) curve. The ROC curve is explained in detail, including how it is generated and interpreted, with an emphasis on the Area Under the Curve (AUC) metric. The PR curve is also discussed, highlighting its use in evaluating classification performance, especially in imbalanced datasets. The paper includes illustrative examples to demonstrate how these metrics are calculated and how they behave under different data conditions. It also addresses the robustness of these metrics against imbalanced data and provides a step-by-step approach for plotting ROC, PR, and DET curves. The paper concludes with a discussion on the relationships between different assessment methods and their applications in real-world scenarios.