Forecasting inflation in Latin American countries using a SARIMA–LSTM combination
نویسندگان
چکیده
Inflation forecasting has been and continues to be an important issue for the world’s economies. Governments, through their central banks, watch closely inflation indicators make national decisions policies. This study proposes forecast rate in five Latin American emerging economies based on commonly used seasonal autoregressive integrated moving average (SARIMA) approach combined with long short-term memory (LSTM). Additionally, we run forecasts fuzzy inference systems (FISs), artificial neural networks (ANNs), neuro-FIS, SARIMA ANN as benchmarks compare performance of combines SARIMA–LSTM. The SARIMA–LSTM captures linear aspects time series well nonlinear aspects. results indicate that proposed model combination LSTM higher accuracy over separately.
منابع مشابه
Deforestation and credit instability in Latin American countries Deforestation and credit instability in Latin American countries
This paper highlights the link between deforestation and credit instability in Latin American countries which exhibit strong deforestation rates as well as macroeconomic instability that is often rooted in the alternating episodes of credit booms and crunches. Pieces of explanation establishing a causal link between credit instability and deforestation driven by agricultural expansion are put f...
متن کاملIncome Convergence toward USA: New Evidences for Latin and South American Countries
Abstract In this paper we test two versions of convergence hypothesis namely deterministic or conditional convergence and stochastic or catching up hypothesis using Carrion-i-Silvestre et al. (2005) stationary test. The results show Latin and South American countries (LSA) catching up process toward the USA failed in 1980s and somewhat in 1990s. But in 2000s most of them could lie in converge...
متن کاملInflation Forecasting using a Neural Network
This paper evaluates the usefulness of neural networks for inflation forecasting. In a pseudo out-of-sample forecasting experiment using recent U.S. data, neural networks outperform univariate autoregressive models on average for short horizons of 1 and 2 quarters. A simple specification of the neural network model and specialized estimation procedures from the neural networks literature appear...
متن کاملNPHS2 Mutations: A Closer Look to Latin American Countries
Nephrotic syndrome is one of the most common kidney pathologies in childhood, being characterized by proteinuria, edema, and hypoalbuminemia. In clinical practice, it is divided into two categories based on the response to steroid therapy: steroid-sensitive and steroid resistant. Inherited impairments of proteins located in the glomerular filtration barrier have been identified as important cau...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Soft Computing
سال: 2021
ISSN: ['1433-7479', '1432-7643']
DOI: https://doi.org/10.1007/s00500-021-06016-5