Аннотация:http://ceur-ws.org/Vol-2523/https://dspace.kpfu.ru/xmlui/handle/net/151948In this work, we address the problem of anomaly detection in largeastronomical databases by machine learning methods. The importance of suchstudy is justified by the presence of a large amount of astronomical data thatcannot be processed only by human resource. We focus our attention on findinganomalous light curves in the Open Supernova Catalog. Few types of anomaliesare considered: the artifacts in the data, the cases of misclassification and thepresence of previously unclassified objects. On a dataset of ~ 2000 supernova(SN) candidates, we found several interesting anomalies: one active galacticnucleus (SN2006kg), one binary microlensing event (Gaia16aye),representatives of rare classes of SNe such as super-luminous supernovae, andhighly reddened objects.