UnFEAR : Unsupervised Feature Extraction Clustering with an Application to Crisis Regimes Classification.

We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes into t...

وصف كامل

التفاصيل البيبلوغرافية
التنسيق: دورية
اللغة:English
منشور في: Washington, D.C. : International Monetary Fund, 2020.
سلاسل:IMF Working Papers; Working Paper ; No. 2020/262
الوصول للمادة أونلاين:Full text available on IMF