Nowadays, Liver Disease (LD) is a very common clinical problem for human health and is related to morbidity and mortality. Nevertheless, an earlier prognosis of LD patients gets a scope to avoid, prior diagnosis and subsequent treatment. This research work attempts to implement a high qualified performer machine learning design to predict LD, the most wanted and unwanted risk factor of LD which could help physicians in classifying risky patients and create an analysis to restrict and control LD. The proposed research study has included all patients, who were identified as having liver diseases. Totally, 6 (six) machine learning algorithms such as Decision Tree(DT), Logistic Regression(LR), Multilayer Perceptron(MLP), Artificial Neural Network(ANN), Random Forest(RF), K Nearest Neighbor classifier(KNN) are selected to predict LD. The location underneath had been utilized to evaluate the accuracy among the six applied models. An overall total of 583 instances had been included in this scholarly research; of the 416 patients are affected by liver illness. The location which defines the receiver operating characteristic (AU ROC) of Logistic Regression, Decision Tree, Multilayer Perceptron, Random Forest, Artificial Neural Network, and K-Nearest Neighbor classifier with 10-fold-cross validation was performed. Furthermore, the reliability of LR, DT, MLP, RF, ANN and KNN with accuracy 72.89%, 81.32%, 60.24%, 86.14%, 75.61%, and 65.52%. The utilization of woodland which is certainly arbitrary within the medical setting may help doctors to detect and classify liver patients for major avoidance, surveillance, quick treatment, and management. LR, DT, MLP, RF, ANN, and KNN formulas are acclimatized to forecast and after analyzing the data set, an increased price of accuracy is achieved.