Optimizing e-commerce marketing strategies in the digital economy: a big data approach enhanced by genetic algorithms

The rapid growth of the digital economy has created both opportunities and challenges for e-commerce businesses, particularly in developing marketing strategies that are data-driven, adaptive, and customer-focused. This study proposes a novel optimization framework that integrates genetic algorithms (GAs) with big data analytics to systematically enhance e-commerce marketing performance. The framework incorporates three core elements: structured product management, personalized content delivery, and data-driven social media promotion. To evaluate its effectiveness, the model was applied across three e-commerce firms in China, representing small, medium, and large business scales. The results demonstrate substantial improvements in key performance indicators: customer satisfaction increased by 21%, advertising strategy effectiveness improved by 0.35 points, and promotional campaign reliability rose by 0.36 points. In addition, Marketing Program Probity scores advanced from 0.60 to 0.91, while Promotion Strategy Completion scores increased from 0.53 to 0.88. These outcomes provide empirical evidence that GA-enhanced optimization can deliver measurable benefits across different organizational sizes. By bridging computational intelligence with real-world marketing practice, the study offers a practical, scalable pathway for e-commerce firms seeking sustained competitive advantage in increasingly data-intensive and competitive digital markets.