Liver Cirrhosis develops into a persistent liver ailment after healthy liver tissue transforms into scar tissue. The tissue replacement occurs with scar tissue formation in liver cirrhosis. Traditional diagnostic methods are expensive and time-consuming. We have used machine learning to create a fast and accurate model for detecting liver cirrhosis in a non-surgical manner. The application of Liver Cirrhosis medical analysis depends on Machine Learning models including Linear Regression alongside Logistic Regression and Decision Tree alongside Random Forest and trained the model using a Liver Cirrhosis Detection dataset. Our model achieved 99.09% accuracy in training and 97.86% in testing. To further make sure that the model is effective, we tested it on three other datasets—Cirrhosis Prediction, Indian Liver Patient Dataset, and Predict Liver Diseases (1700 records)—where we have achieved an accuracy above 97%. In the future, we aim to improve the model by testing it on custom datasets.