Liver disease is the leading reason of death worldwide, The liver is responsible for metabolic, strength-storing, and waste-filtering functioning in your body. The aim of this study is to develop a machine learning-based technique for liver disease prediction in people. This study on liver disease detection models is meant to determine the best techniques for selecting and synthesizing the many studies of high quality. The majority of health data is nonlinear, correlation-structured, and complex, making it complex to evaluate. The use of ML-based techniques in healthcare has been ruled out. This work uses various machine learning algorithms like decision trees, Naïve Bayes, SVM, Random Forest, CatBoost, and Soft Voting Classifier on the Indian Liver patient dataset to predict liver disease. The research work gives the correct or maximum accuracy model showing that the model is able to predict liver diseases effectively. Our end result shows that the Voting classifier attains higher accuracy as compared to other machine-learning models