Master of Science (MS)
Program or Discipline Name
This paper investigates the impact of secondary ranking factors on webpage relevance and rankings in the context of Search Engine Optimization (SEO), focusing on the jewelry domain within the United States e-commerce market. By generating a keyword list related to jewelry and retrieving top URLs from Google's search results, the study employs machine learning models including XGBoost, CatBoost, and Linear Regression to identify key features influencing webpage relevance and rankings.The findings highlight specific optimal ranges for features like Outlinks, Unique Inlinks, Flesch Reading Ease Score, and others, indicating their significant impact on better rankings. Notably, Random Forest model performed best with a Mean Average Error of 1.6, showcasing its accuracy in predicting rankings within the 1-10 range. Through compelling visualizations like horizontal bar charts, key features such as external outlinks, response time, and average words per sentence are effectively presented.The research contributes valuable insights into the evolving landscape of SEO, emphasizing the practical implications of recognizing these optimal feature ranges for informing businesses' SEO strategies. This study underscores the dynamic nature of SEO and the importance of continuous exploration in this field.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Abdyyev, A. (2023). Secondary features of importance for a url ranking. Retrieved from https://digitalcommons.harrisburgu.edu/anms_dandt/3