Research and Prediction Based on Multiple Linear Regression and Machine Learning

In this paper, a multivariate linear regression model is built for prediction based on SBPE Dataset by drawing heat maps to select relevant features. All 80% of the data is used as a training set. The remaining 20% was divided into 5 variants as a test set. The accuracy of the model in estimating the predicted and true values of the different variables was calculated by comparing their RMSE and R 2 scores. The results show that the precision is different between the different variables. In addition, this paper discusses whether the predictions of the same sailboat are affected by the region and whether they vary significantly across sailboat types within the same region.