Research on Tourism Demand Forecasting Model Based on Machine Learning Algorithm

The passenger flow of rural tourism is influenced by various factors, such as season, weather, holidays, etc. The complex factors make the prediction model less accurate in predicting passenger flow. This article applied the Autoregressive Integrated Moving Average (ARIMA) model. By improving the crossover operation of genetic algorithm and utilizing multi-point crossover to optimize the parameters of ARIMA model, the accuracy of model prediction was improved. The prediction results before and after optimization were compared. The experimental results showed that the application of genetic algorithm could achieve an average accuracy of about 93.3 % in predicting passenger flow using the autoregressive integrated moving average model, and the model achieved significant improvement in the accuracy of passenger flow prediction.