Water quality prediction is one of the important contents water-related problems. Through water quality prediction, we can find signs of water quality deterioration and facilitate decision-makers to take measures in advance. The water quality prediction model based on genetic algorithm and SVM is used to adapt the weight of pollution in current application to improve the accuracy. The model first uses the genetic algorithm to train the feature weight vector of data to confirm feature weight adapts to the current application, and then apply the feature weight vector in the SVM model training. After conducting experiments with a sewage treatment plant in Chongqing, the feasibility of the model in practical application was verified, this provided a new idea for water quality prediction.