Consumer Behavior Analysis and Enterprise Marketing Strategy Optimization Based on Decision Tree Model and Association Rule Algorithm

Abstract

With the rapid advancement of big data technology, enterprises are encountering increasingly complex market environments, making consumer behavior patterns harder to predict. This study leverages big data analysis to explore the relationship between consumer behavior and corporate marketing strategies. Using a combination of decision tree models and association rule algorithms, we analyze the purchasing behaviors of 1,000 consumers in Shenyang City. The results indicate that personalized marketing and dynamic pricing strategies significantly enhance sales growth and customer loyalty. Specifically, dynamic pricing strategies resulted in a 16.7% increase in sales growth, while personalized promotions led to a 10.5% increase in customer retention. The decision tree model achieved an accuracy of 89.5%, with key performance metrics including precision, recall, and F1-score being evaluated for model performance. Furthermore, the association rule algorithm identified frequent purchase patterns with a support degree of 0.25 and a confidence degree of 67%. These findings highlight the importance of accurate consumer behavior analysis in optimizing marketing strategies, improving market competitiveness, and increasing customer loyalty. The study demonstrates that big data-driven approaches can effectively guide enterprises in making data-informed, real-time marketing decisions.