Liver disease is a critical health concern that can lead to severe complications or death if not diagnosed early. Machine learning techniques offer promising avenues for improving the accuracy and efficiency of liver disease prediction. This research paper proposes a comprehensive machine learning-based framework for the prediction and classification of liver diseases. The study utilizes a dataset comprising medical records and liver function test results to train and evaluate multiple machine learning models. The proposed framework incorporates various algorithms, including Logistic Regression, Random Forest, Support Vector Machines (SVM), and Ensemble Learning techniques, to enhance predictive accuracy. The data preprocessing steps include handling missing values, normalization, and feature selection to optimize model performance. Each model's effectiveness is assessed based on accuracy, sensitivity, specificity, and F1 score, with the Random Forest and Ensemble models demonstrating superior performance. This research contributes to the field of medical diagnostics by providing a reliable and accurate tool for the early detection and classification of liver diseases, potentially improving patient outcomes through timely intervention.