The healthcare industry has been using data mining to anticipate diseases in recent years. The process of retrieving or transforming specific information from sizable archives, warehouses, or other databases is known as data mining. For academics, predicting the illnesses from the vast medical information is a highly challenging task. To overcome this issue, the researchers employ data mining techniques such as clustering, grouping, and association rules, among others. The primary objective of this research is to predict liver disorders using classification algorithms. The techniques utilized in this paper are support vector machine (SVM), random forest, and naive bayes. These categorization methods are contrasted based on their accuracy and performance. The performance and accuracy of Naïve Bayes and Support Vector Machine algorithms are examined and compared with the algorithm outcomes. In order to assess the accuracy and performance, we employed a dataset known as ILDP. Aspects including Name, Age, Total Bile, Sgpa, Sgpt, and so on are included in this dataset. When compared to other algorithms, the Support Vector Machine had the most accurate performance and accuracy.