Geometallurgical domaining involves the characterisation of subsurface material, to predict how the material will respond to mining processes such as blast fragmentation, loading, material handling, crushing, grinding, flotation and leaching. Conventional geological mapping, traditional sample logging, and automated scanning technology typically inform geometallurgical domains using textural and mineralogical observations, e.g., grain size or sulphide content. Where geochemical sampling is routinely done, the possibility exists to quickly produce geochemically-based geometallurgical domains. At the mine-scale, such domains represent a cost-effective, first-pass decision-making tool to subdivide mining areas using robust measures. These geochemical domains can then be assessed for further geometallurgical study.Geochemical-geometallurgical domains can be identified using multivariate data analysis combined with machine learning pattern-recognition techniques (Keeney, 2010; Montoya et al. 2011). Using this methodology, it is possible to consider many chemical elements in a dataset simultaneously. Geochemical domains can reflect mineralogy to a degree that might be difficult or impossible to produce using geological mapping, visual logging, or considering geochemical data in conventional ways (Berry et al., 2011; Cobeas et al., 2015). Unfortunately, there are very few published studies that examine geochemical domaining of mineral deposits (e.g. Caciagli, 2015; Gazley et al., 2015; Gazley & Collins, 2016). Here we address that shortcoming by presenting our workflow and illustrating it using datasets from mineral deposits around the Pacific Rim, including Cu-porphyry, orogenic Au, epithermal Au, Carlin-style mineralisation and granodiorite-hosted Cu-Ag-Au. Clustering algorithms are present as an efficient method to group co-varying elements. CITATION: Gazley, M F, Caciagli, N, Hood, S B and McFarlane, A, 2019. Multivariate data analysis and machine learning towards robust geometallurgical domains: examples from the Pacific Rim, in Proceedings PACRIM 2019, pp 114116 (The Australasian Institute of Mining and Metallurgy: Melbourne).