Research on Factors Affecting Weight Based on Machine Learning Algorithm

In view of the increasing prevalence of overweight and obesity in Chinese residents, in order to explore the factors affecting weight, three machine learning models based on logical regression algorithm, decision tree algorithm and random forest algorithm are constructed to explore the factors affecting weight. The model is continuously optimized by parameters and cross-validation, and the performance of the model is evaluated by using four indicators: accuracy, precision, recall and the harmonic average of the two. The results show that the accuracy of logistic regression algorithm, decision tree algorithm and random forest algorithm are 0.65, 0.75 and 0.8 respectively, which shows that the decision tree algorithm and random forest algorithm can better complete the classification and prediction of weight influencing factors, and the random forest algorithm has the best classification and prediction effect, which can be used for researchers and practitioners in the field of nutrition and health reference.