This study aims to find out how to classify water quality, accuracy and efficiency in the water quality classification process using the Random Forest method. This system is built through a website-based application that uses the Python programming language, HTML, CSS, Javascript and the Flask framework. In addition, this study uses the Rapid Application Development software development method. This method allows the development team to respond quickly and flexibly to changing needs. This method consists of several development cycles, each of which consists of requirements planning, system design, modeling, model testing, refinement, development, implementation, and evaluation. The results of the study show that the RF model has an accuracy level, is 78% with a precision 83%, recall 80%, and fi-score value of 82%. Overall, this study successfully shows that the application of RF algorithms to the water quality classification system through a website-based application gives very impressive results in terms of accuracy. The Rapid Application Development approach also helps in dealing with changes and challenges in the software development process. The results of this research can make an important contribution to further development in the field of water quality recognition.