This paper proposes a solution aimed at optimizing recommendation systems for online commerce. Taking an ordered list of products to recommend as input, the proposed solution optimizes this list by considering trends in web searches. The solution collects data on web search trends, filters the data to retain only searches related to products and services, identifies the relevant characteristics of these products, and subsequently reorders the recommendation list based on the similarity of these characteristics with the characteristics of the products on the recommendation list. This establishes a relationship between market search trends and the most recommendable products/services from the existing offer. The solution adopts the power of Google Trends to capture consumer interest across various topics, products, and services—it is assumed that web search trends reflect market trends. Second, ChatGPT is added to refine the gathered raw trend data by removing noise, contextualizing information and matching it with the attributes of products or services in the recommendation list, ensuring that the trend insights are relevant and actionable. Finally, it integrates these insights with the user preferences to dynamically reorder the recommendation lists, prioritizing items that are most representative. Initial results show its effectiveness in improving the relevance of recommendations by demonstrating its potential as a scalable and automated framework for optimizing digital marketing campaigns to build adaptive recommendation engines. This approach provides a robust foundation for future innovations by aligning user preferences with external market signals.