Friction and wear are very common phenomena found virtually everywhere. However, it is very difficult to predict tribological (i.e. related to friction and wear) structure–property relationships from fundamental physical principles. Consequently, tribology remains a data-driven, mostly empirical discipline. With the advent of new machine learning (ML) and artificial intelligence methods, it becomes possible to establish new correlations in tribological data to predict and control better the tribological behavior of novel materials. Hence, the new area of triboinformatics has emerged combining tribology with data science. This paper reviews ML algorithms used to establish correlations between the structures of metallic alloys and composite materials, tribological test conditions, friction and wear. This paper also discusses novel methods of surface roughness analysis involving the concept of data topology in multidimensional data space, as applied to macro- and nanoscale roughness. Other triboinformatic approaches are considered as well.