Water is considered the most important element for humans and other living organisms. However, escalating pollution and the impacts of climate change necessitate the analysis of groundwater quality, which is imperative for ensuring safe water. Due to its scalability, robustness, and reduced susceptibility to overfitting, the Random Forest (RF) classifier method was used to calculate the water quality index for the classification of water quality. The groundwater quality in the research area is forecasted by constructing a Random Forest model utilising the arithmetic Water Quality Indices (WQI), which encompass the key elements affecting groundwater quality, including pH, temperature, nitrate, phosphorus, and other chemical parameters. The F1 score, accuracy, recall, and precision are used to evaluate the performance. The model achieved a satisfactory performance, with an overall accuracy of 96%, an F1 score of 99% for the excellent class, and a score of 97% for the unsuitable class. In addition, excellent water quality constitutes 55% of the samples; however, concerns persist for poor and unsuitable classes, which comprise 10% and 16% of the samples, respectively. Furthermore, the feature analysis revealed that the most important variables influencing the quality of the groundwater in the study region are Escherichia coli (E. coli) and phosphorus. The study provided significant insights into the groundwater quality of the study area, establishing a basis for future research and the development of effective groundwater management policies.