Deep learning models for inflation forecasting
Carregando...
Autores
Orientador
Co-orientadores
Citações na Scopus
Tipo de documento
Artigo Científico
Data
2023
Título da Revista
ISSN da Revista
Título do Volume
Resumo
We propose a hybrid deep learning model that merges Variational Autoencoders and Convolutional LSTM Networks (VAE-ConvLSTM) to forecast inflation. Using a public macroeconomic database that comprises 134 monthly US time series from January 1978 to December 2019, the proposed model is compared against several popular econometric and machine learning benchmarks, including Ridge regression, LASSO regression, Random Forests, Bayesian methods, VECM, and multilayer perceptron. We find that VAE-ConvLSTM outperforms the competing models in terms of consistency and out-of-sample performance. The robustness of such conclusion is ensured via cross-validation and Monte-Carlo simulations using different training, validation, and test samples. Our results suggest that macroeconomic forecasting could take advantage of deep learning models when tackling nonlinearities and nonstationarity, potentially delivering superior performance in comparison to traditional econometric approaches based on linear, stationary models.
Palavras-chave
Vínculo institucional
Titulo de periódico
Applied Stochastic Models in Business and Industry
Título de Livro
URL na Scopus
Idioma
Inglês
URL permanente
Notas
Membros da banca
Área do Conhecimento CNPQ
CIENCIAS EXATAS E DA TERRA::MATEMATICA
CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA
ENGENHARIAS::ENGENHARIA ELETRICA
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
CIENCIAS SOCIAIS APLICADAS::ECONOMIA
CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA
ENGENHARIAS::ENGENHARIA ELETRICA
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
CIENCIAS SOCIAIS APLICADAS::ECONOMIA