Research on Industrial Value Added Forecasting Model Based on Integrated Algorithm
The rapid development of China's industrial economy makes accurate forecasting of industrial value added a crucial task.Industrial value added plays an important role in the economy,and its effective current forecasting helps to analyze the macroeconomic direction in time.The study adjusts the key parameters of six integrated algorithms such as Gradient Boosted Decision Tree(GBDT),Random Forest Regression(RFR),LightGBM,Adaboost,XGBoost and CatBoost by applying Particle Swarm Optimization(PSO)algorithm in order to improve the performance of these algorithms in the forecasting of value added of industry,and selects MSE,MAE,accuracy as model evaluation indexes.The experimental results show that,comparing the model indexes after particle swarm optimization,the models are ranked according to their predictive performance:XGBoost＞AadBoost＞CatBoost＞RFR＞LightGBM＞GBDT.The XGBoost model based on the particle swarm optimization algorithm shows better predictive effect in industrial value added prediction,which provides powerful support for improving the accuracy of industrial economic It provides strong support for improving the accuracy of industrial economic prediction.
industrial value added forecastingparticle swarmparameter optimizationintegrated learningXGBoost algorithm model
NETL
NSTL
万方数据
