Abstract: Among the most prevalent harmful diseases in the world, liver disease has been on the rise in recent decades and is predicted to keep rising. Researchers found it extremely difficult to predict the disease using massive medical data sets. They are using machine learning strategies like clustering and classification to tackle this issue. The primary goal of the research is to employ classification algorithms to predict a patient’s likelihood of getting liver disease. The contrast of these algorithms is based on how effectively they identify data and how quickly they run. Taking into account these performance variables, the algorithm which functions as a more effective classifier is chosen. A liver disease that continues for more than six months is referred to be a chronic condition of the liver. Therefore, the proportion of patients who get the disease will be used to provide both positive and negative information. Classifiers have been employed to process liver disease percentages, and the result is shown as a confusion matrix. When a training data set is available, we offer several classification strategies that can significantly enhance classification performance. Subsequently, excellent, and poor values are identified using a machine learning classifier.