Hepatocellular carcinoma (HCC) is the most common primary liver cancer and is often associated with chronic liver diseases such as hepatitis and cirrhosis. It is a leading cause of cancer-related deaths worldwide due to its aggressive nature and late-stage diagnosis. This study aims to enhance the prediction of HCC survivability by using advanced machine-learning techniques. The proposed module utilizes ridge regression for feature selection to identify key pathological features, followed by decision tree classification to predict survivability. The detection framework examines the HCC dataset to determine whether it suffers from class imbalance. If the dataset suffers from imbalance, synthetic minority oversampling technique (SMOTE), random oversampling, and random undersampling are used to resample the dataset. The sampled data obtained through various sampling techniques are then passed to different machine learning classifiers, including Support Vector Machine (SVM), naive Bayes, decision tree, and logistic regression, and the best sampling technique and classifier are identified. When applied to the balanced SMOTE samples, the decision tree has been identified as the best classifier. The SMOTE-based samples are then passed through various feature selection techniques such as Mutual Information, Fisher Score, Sequential Forward Feature Elimination (SFFE), Sequential Backward Feature Elimination (SBFE), LASSO Score, and Ridge Regression, and these features are again classified using SVM, naive Bayes, decision tree, and logistic regression supervised classifiers. The study found that the ridge regression features best identified pathological features. Using only three pathological features selected through ridge regression, decision tree and SVM revealed the highest accuracy of 87.88%.