Research on Enterprise Decision Support Systems Based on Artificial Intelligence Technology

In response to the challenge of optimizing decision support systems (DSS) for enterprises in the big data environment, this paper introduces the C4.5 decision tree algorithm and the improved Apriori algorithm, aiming to improve the classification accuracy and data correlation mining effect of the system through data mining techniques. Firstly, this paper theoretically analyzes the principles and optimization directions of C4.5 and Apriori algorithms; then, algorithm application testing is conducted on actual datasets to verify the effectiveness of the algorithm in different business scenarios, especially in the fields of retail and finance. Finally, the experimental results show that the C4.5 algorithm exhibits high accuracy and F1 score in classification task. The results show that the C4.5 decision tree algorithm effectively improves the accuracy of classification tasks, reaching 85%, with an F1 score of 85%, which is better than traditional decision tree algorithms. The model and method proposed in this paper provide new technical support and optimization directions for enterprises in big data decision support.