Search Results

You are looking at 1 - 10 of 50 items for :

  • "deep learning" x
Clear All
Mr. Jorge A Chan-Lau

data clusters: non-separability and time clustering Figure 3: Raw data clusters: country bias and imbalanced data To perform feature engineering step we use autoencoders , which are commonly used in machine learning and deep learning, with a suitable loss function designed with the purpose to to address the first three issues described above, i.e. lack of separability in the data points, time clustering, and country clustering. After some experimentation, we fall back on the Synthetic Minority Over-sampling Technique (SMOTE) to address the data

Mr. Jorge A Chan-Lau
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 time-invariant non-overlapping clusters, each of which could be identified with a different regime. The likelihood that a country may experience an econmic crisis could be set equal to its cluster crisis frequency. Moreover, unFEAR could serve as a first step towards developing cluster-specific crisis prediction models tailored to each crisis regime.
Ms. Ghada Fayad, Chengyu Huang, Yoko Shibuya, and Peng Zhao

training a deep learning model to recognize the nature of sentiments from the description of authorities’ views. Our topic model, which combined several techniques, was able to assign the correct topics 89 percent of the time, while our trained deep learning model was able to estimate the correct sentiment (as labeled by the team in a test set) 81 percent of the time, both suggesting very high performance of the model in relation to the related literature. 4 Our findings suggest that authorities have generally appreciated or had “positive” initial reactions to Fund

Jelle Barkema, Mr. Mico Mrkaic, and Yuanchen Yang
This paper dives into the Fund’s historical coverage of cross-border spillovers in its surveillance. We use a state-of-the-art deep learning model to analyze the discussion of spillovers in all IMF Article IV staff reports between 2010 and 2019. We find that overall, while the discussion of spillovers decreased over time, it was pronounced in the staff reports of some systemically important economies and during periods of global spillover events. Spillover discussions were more prominent in staff reports covering advanced and emerging market economies, possibly reflecting their role as sources of global spillovers. The coverage of spillovers was higher in the context of the real, financial, and external sectors. Also, countries with larger economies, higher trade and capital account openess and lower inflation are more likely to discuss spillovers in their Article IV staff reports.
Ms. Ghada Fayad, Chengyu Huang, Yoko Shibuya, and Peng Zhao
This paper applies state-of-the-art deep learning techniques to develop the first sentiment index measuring member countries’ reception of IMF policy advice at the time of Article IV Consultations. This paper finds that while authorities of member countries largely agree with Fund advice, there is variation across country size, external openness, policy sectors and their assessed riskiness, political systems, and commodity export intensity. The paper also looks at how sentiment changes during and after a financial arrangement or program with the Fund, as well as when a country receives IMF technical assistance. The results shed light on key aspects on Fund surveillance while redefining how the IMF can view its relevance, value added, and traction with its member countries.
Jelle Barkema, Mr. Mico Mrkaic, and Yuanchen Yang

interest rates in 2015, and the ECB’s expanded asset purchase program (APP) in 2015 and 2016. On the non-monetary policy side, Brexit-related risks and global trade tensions that heightened in 2018–19 also dominated spillover concerns in the global platform. With the use of a state-of-the-art deep learning model, we analyze the discussion of spillovers in all IMF Article IV staff reports during 2010 and 2019. We find that while the discussion of spillovers has overall declined in this period, it spiked during specific years that overlapped with the major monetary