The paper explores the use of large language models (LLM) to optimize SEO processes to increase organic traffic for e-commerce platforms. The possibilities of scalable adaptation of large content volumes to the requirements of search algorithms using tools built on the basis of LLM are considered. A comparative analysis of the effectiveness of new automated SEO optimization methods and traditional manual tuning approaches is conducted using the example of an e-commerce platform with a wide range of products and a high level of traffic. The results demonstrate a significant reduction in SEO optimization time (up to 85% in the case of large catalogs), improved metadata quality, and a significant increase in organic traffic. Key advantages of implementing LLM are identified, including scalability, parallel processing, ensuring consistency of SEO standards for old positions, and rapid adaptation to changes in search algorithms. The study confirms the effectiveness of integrating LLM into the SEO workflow of e-commerce platforms to achieve sustainable growth in organic traffic.
[1] Entities In SEO: What Are They And Why Do They Matter? [Електронний ресурс] – Режим доступу до ресурсу: https://www.searchenginejournal.com/entity-seo/492947/
[2] An SEO guide to understanding E-E-A-T [Електронний ресурс] – Режим доступу до ресурсу: https://searchengineland.com/guide/google-e-e-a-t-for-seo
[3] Henry Jones July 2, 2025 “The Impact of AI and LLM on Your Organic Traffic” [Електронний ресурс] – Режим доступу до ресурсу: https://proof3.co/insights/impact-of-ai-and-llm-on-organic-traffic
[4] Google Search Central Blog (2024). "Google Search's guidance about AI-generated content". [Електронний ресурс] – Офіційна позиція Google щодо контенту, створеного за допомогою штучного інтелекту: https://developers.google.com/search/blog/2023/02/google-search-and-ai-content
[5] Schweidel D., Knox G., et al. Moving Beyond ChatGPT: Applying Large Language Models in Marketing Contexts. – Journal of Marketing Research & Innovation, 2024. – Sciendo. – 14 с. – https://doi/org/10.2478/nimmir-2024-0004
[6] Aggarwal P., Murahari V., Rajpurohit T., Kalyan A., Narasimhan K., Deshpande A. GEO: Generative Engine Optimization. – KDD ’24 Proceedings. – ACM, 2024. – 12 с.
[7] Chodak G., Błażyczek K. Large Language Models for Search Engine Optimization in E-commerce / Grzegorz Chodak, Klaudia Błażyczek. – ResearchGate, 2024. – 15 с., https://doi/org/10.1007/978-3-031-56700-1_27
[8] Henry Jones July 2, 2025 “The Impact of AI and LLM on Your Organic Traffic” [Електронний ресурс] – Режим доступу до ресурсу: https://proof3.co/insights/impact-of-ai-and-llm-on-organic-traffic
[9] AI Statistics 2025: Top Trends, Usage Data and Insights [Електронний ресурс] – Режим доступу до ресурсу: https://www.synthesia.io/post/ai-statistics
[10] What is RAG (Retrieval-Augmented Generation)? [Електронний ресурс] – Режим доступу до ресурсу: https://aws.amazon.com/what-is/retrieval-augmented-generation/
[11] Boonstra, L. (2023). Prompt Engineering. O’Reilly Media.