Weight class prediction based on sparrow search algorithm optimised random forest model

Abstract

In this paper, we improve the traditional random forest model by optimising the random forest algorithm based on sparrow search algorithm and compare the effectiveness of the two models for weight class prediction. Initial exploration of the data revealed that age, height, weight and BMI play an important role in weight class prediction. Correlation analyses showed a strong correlation between age and BMI and weight class. The experimental results show that the random forest model optimised based on the sparrow search algorithm achieves 100% in prediction accuracy, which improves the accuracy by 1.2% compared with the traditional random forest algorithm, and has better prediction effect. The significance of this paper is that a random forest algorithm optimised based on the sparrow search algorithm is proposed and experimentally demonstrated to have better performance in weight class prediction. This is of great significance in the fields of weight management, health assessment, and disease risk assessment. In addition, this study demonstrates the value of data analysis and machine learning methods in solving real-world problems. In conclusion, this paper provides new ideas for further improvement and application of machine learning algorithms, and provides references and lessons for researchers in related fields.