STATISTICAL MACHINE LEARNING APPROACHES TO LIVER DISEASES PREDICTION, In this research, the aim was to develop a computer model that can accurately predict liver disease using various classification algorithms such as random forests, perceptrons, decision trees, K nearest neighbors, and support vector machines. The study used data from the UCI repository on liver patients and analyzed and optimized features to improve prediction performance. The results showed that the support vector machine algorithm had the highest accuracy at 78.3%. This model was used to create a system that allows users to enter their blood test report information and receive a prediction of their risk for liver disease. The goal of this work was to improve medical diagnosis through the use of machine learning techniques and to provide clinicians with a tool to assess the risk of liver disease in their patients., liver disease; Machine Learning, Random Forest, KNN, Decision Tree, Supported Vector Machine, 4 Members, Team Member, Supporting role, Machine Learning, Random Forest, KNN, Decision Tree, Supported Vector Machine, Anaconda Navigator, Jupyter Notebook, python, 08/22, 11/22, IBM NALAIYA THIRAN PROJECT