Cognitive symptoms are a central feature of most psychiatric diseases including psychotic and affective disorders. Recent results, including work from our lab (Kambeitz-Ilankovic et al., 2019), demonstrated that cognitive training can effectively improve cognitive performance in patients with psychosis. However, there is substantial variability with respect to how individuals patients respond to the treatment: while some show the desired treatment effect, some patients do not respond. Thus in the current project we aim to employ machine learning techniques to create tools that allow individualised prediction of treatment response to cognitive training. The ultimate goal is to personalise cognitive training and to provide efficient interventions according to the novel paradigm of precision psychiatry.