OPTIMAL-EM

A web accessibility evaluation methodology proposed by Hambley, Yesilada, Vigo, and Harper to complement the W3C's WCAG-EM by providing a statistically grounded, complexity-driven method for selecting representative pages from a large website. OPTIMAL-EM comprises six metrics — coverage, representativeness, complexity, popularity, freshness, and accessibility — and uses clustering (typically t-SNE plus DBSCAN over vector-space models of HTML structure) to group similar pages, then prioritises audit effort toward clusters with high within-cluster complexity variance, which empirically predict higher barrier prevalence. It is designed to reduce the manual audit burden on large sites while improving the defensibility of sampling decisions under regulations such as the EU Web Accessibility Directive.