AI-DRIVEN APPROACHES TO REDUCING WEB PAGE LOAD TIME

Authors

  • Nigorakhon Khamidjonova Botir qizi Master student, Sharda University Uzbekistan Author

Keywords:

Artificial intelligence, machine learning, web performance, page load time, frontend development, Core Web Vitals, predictive prefetching, image optimization, adaptive loading, performance monitoring.

Abstract

 Load time is one of the main factors that determine whether a visitor stays on a website, and conventional optimization relies on fixed rules written in advance by a developer. This thesis considers how artificial intelligence (AI) and machine learning (ML) can make load time optimization adaptive. Five directions are examined: predictive prefetching, intelligent media optimization, adaptive loading, AI-assisted code optimization and intelligent performance monitoring. A four-stage cyclic model that combines these directions is proposed, together with a plan for evaluating it by Core Web Vitals metrics.

References

1.Walton P. Web Vitals. – web.dev, Google, 2020. – URL: https://web.dev/articles/vitals

2.McQuade B. How the Core Web Vitals metrics thresholds were defined. – web.dev, Google, 2020. – URL: https://web.dev/articles/defining-core-web-vitals-thresholds

3.The need for mobile speed: How mobile latency impacts publisher revenue. – Think with Google, 2016. – URL: https://www.thinkwithgoogle.com

4.Guess.js: Libraries and tools for enabling machine learning driven user experiences on the web. – URL: https://github.com/guess-js/guess

Downloads

Published

2026-11-11