The liver is the most important and one of the largest organs in the body. The Liver serves a number of functions, making it vital to the human body. When the Liver’s regular functions are disrupted, it becomes a disrupted Liver. The number of liver patients has been significantly growing in recent years, making improved liver disease detection a challenging aspect of health care. The use of an automated diagnostic system can assist in identifying liver disease and improve diagnostic accuracy. As a consequence, we have used machine learning classification techniques like Logistic Regression, Gaussian Naïve Bayes, Stochastic Gradient Descent, KNN, Decision Tree, Random Forest, and SVM to design a more accurate diagnostic model. All these algorithms have implemented on the ILPD dataset with the intension to reduce time of diagnosis and earlier prediction of disease. In Future the accuracy of classification will be enhanced by feature extraction and the big dataset can also be examined for training the model and determining algorithms.