Water quality assessment is crucial for environmental management and public health, particularly in regions like Kerala, India, where rivers play a vital role in the ecosystem and human activities. This study investigates the water quality of 44 rivers in Kerala, India, using machine learning techniques to classify water quality based on specific parameters. The data, sourced from the Kerala State Pollution Control Board's Water and Air Quality Directory 2023, include measurements of pH, biochemical oxygen demand (BOD), dissolved oxygen (DO), electrical conductivity (EC), and total coliform concentration. These parameters were used to categorize water into five distinct classes: Class A (drinking water source without conventional treatment but after disinfection), Class B (outdoor bathing), Class C (drinking water source after conventional treatment and disinfection), Class D (propagation of wildlife and fisheries), and Class E (irrigation, industrial cooling, controlled waste disposal). Three machine learning models were employed for classification: support vector machine (SVM), k-nearest neighbors (KNN), and decision tree (DT). The dataset was split into training and testing sets to evaluate the models' performance. Among the models, the SVM achieved the highest accuracy, classifying water quality with an accuracy of 92.83%. The results demonstrate the effectiveness of machine learning in assessing and classifying river water quality, providing a valuable tool for environmental monitoring and management. This study highlights the potential of advanced data analysis techniques to support public health and environmental conservation efforts by accurately identifying water quality categories based on standardized criteria.