In emerging websites, there is a need to measure and evaluate the websites quality and to make it better understanding. Several metrics based on the dimensions of the criteria are content quality, organization quality, design quality and user-friendly quality. These factors depend upon the word count, page size, average link text count and so on. This research investigates an Improved Grey Wolf Optimization (IGWO) and Extreme Learning Machine (ELM) is proposed to correspond with quality related items. The proposed approach IGWO is compared to verify the performance of Grey Wolf Optimization (GWO) Support Vector Machine (SVM) model, traditional Extreme Learning Machine (ELM) and Ivory based models are made to test the webpages. The performance metrics captured in IGWO based ELM model can be used to predict the website designs are good or bad. The simulation results have proven the superiority of the proposed method over the other competitive counterparts.