Working Paper: CEPR ID: DP14025
Authors: Vadym Lepetyuk; Lilia Maliar; Serguei Maliar
Abstract: The Canadian economy was not initially hit by the 2007-2009 Great Recession but ended up having a prolonged episode of the effective lower bound (ELB) on nominal interest rates. To investigate the Canadian ELB experience, we build a "baby" ToTEM model -- a scaled-down version of the Terms of Trade Economic Model (ToTEM) of the Bank of Canada. Our model includes 49 nonlinear equations and 21 state variables. To solve such a high-dimensional model, we develop a projection deep learning algorithm -- a combination of unsupervised and supervised (deep) machine learning techniques. Our findings are as follows: The Canadian ELB episode was contaminated from abroad via large foreign demand shocks. Prolonged ELB episodes are easy to generate with foreign shocks, unlike with domestic shocks. Nonlinearities associated with the ELB constraint have virtually no impact on the Canadian economy but other nonlinearities do, in particular, the degree of uncertainty and specific closing condition used to induce the model's stationarity.
Keywords: central banking; totem; machine learning; deep learning; supervised learning; neural networks; clustering analysis; large-scale model; new keynesian model; ZLB; ELB
JEL Codes: C61; C63; C68; E31; E52
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Foreign demand shocks (F41) | Canadian ELB episode (Y60) |
| US demand shocks (N12) | Canadian exports (F10) |
| Canadian exports (F10) | Prolonged ELB episode (Y60) |
| Foreign shocks (F69) | Realistic ELB episodes (Y60) |
| Domestic shocks (E32) | Difficulty in achieving ELB episodes (C62) |
| Higher inflation target (E31) | Preventing ELB episode (Y60) |
| ELB constraint (Y80) | Model's performance (C52) |
| Nonlinearities and uncertainty (D89) | Model's predictions (C52) |