Research on the Integrated System of Data Mining and Machine Learning in Economic Decision Support System

This paper proposes an economic decision support system framework that integrates data mining and machine learning algorithms, aiming to improve the scientific and accuracy of the decision-making process. The system first uses data mining technology to preprocess economic data comprehensively, including data cleaning, feature extraction and pattern recognition. Then the system combines multiple machine learning algorithms for decision prediction and optimization. The prediction performance of different algorithms is compared and analyzed for simulation results. The average prediction error of the integrated system on a large-scale economic data set is 5.2%, which is significantly lower than that of a single algorithm (such as the decision tree algorithm, with a prediction error of 8.4%). In terms of accuracy, the integrated model achieved an accuracy of 94.8%, which is superior to the traditional SVM algorithm (with an accuracy of 86.3%). Simulation data show that the integrated model has strong adaptability and high accuracy in different economic scenarios, and its prediction error is significantly lower than that of traditional methods, which can provide more reliable decision support for economic decision makers.