Research on Assembly Time Quota Prediction Model of Toy Products of A Company Based on Improved RFECV and XGBoost Algorithms

The purpose of this paper is to study the prediction of assembly time quota of electronic toy products of A company, and use XGBoost and improved RFECV method to predict and optimize. After analyzing the factors affecting the assembly hours quota of electronic toy products, the assembly hours of different toy products can be accurately predicted by constructing the XGBoost model. In addition, the improved RFECV method is used to select the most influential features to help determine the main factors affecting the assembly hours. Finally, the grid search method is used to find the value of the optimal parameter in XGBoost. Through the analysis of the data of electronic toy manufacturing enterprises, the man-hour error rate is controlled within 10%. The result shows that this method can improve the quality and efficiency of the man-hour quota work of electronic toy products.