2021
DOI: 10.1155/2021/1071145
|View full text |Cite
|
Sign up to set email alerts
|

Inflation Prediction Method Based on Deep Learning

Abstract: Forward-looking forecasting of the inflation rate could help the central bank and other government departments to better use monetary policy to stabilize prices and prevent the impact of inflation on market entities, especially for low- and middle-income groups. It can also help financial institutions and investors better make investment decisions. In this sense, the forecast of inflation rate is of great significance. The existing literature mainly uses linear models such as autoregressive (AR) and vector aut… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(11 citation statements)
references
References 27 publications
0
11
0
Order By: Relevance
“…Harris [23] forecasted the Canadian CPI to predict food prices and compared multi-layer perceptron (MLP), M5P tree, sequential minimal optimization (SMO), and linear regression, with the former resulting in the best mean https:// journal.uob.edu.bh absolute percentage error (MAPE). Yang and Guo [24] used deep learning based on a recurrent neural network to predict the CPI, and consequently inflation, and achieved a mean square error (MSE) of 0.359. In [25], SARIMA was compared to deep neural network with 20 hidden layers, with the latter one achieving a lower MSE of 1.75.…”
Section: Prior Related Workmentioning
confidence: 99%
“…Harris [23] forecasted the Canadian CPI to predict food prices and compared multi-layer perceptron (MLP), M5P tree, sequential minimal optimization (SMO), and linear regression, with the former resulting in the best mean https:// journal.uob.edu.bh absolute percentage error (MAPE). Yang and Guo [24] used deep learning based on a recurrent neural network to predict the CPI, and consequently inflation, and achieved a mean square error (MSE) of 0.359. In [25], SARIMA was compared to deep neural network with 20 hidden layers, with the latter one achieving a lower MSE of 1.75.…”
Section: Prior Related Workmentioning
confidence: 99%
“…LSTM superiorities include the constant backpropagation of errors in memory cells resulting in the ability of LSTM to bridge long-time lags. LSTM can handle noise, distributed representation, and continuity (Yang & Guo, 2021). Shumway & Stoffer (2019) said that time series data {𝑌𝑡} is a series of random and correlated observations arranged according to the time 𝑡 = ±1, ±2, …, ±𝑛.…”
Section: Lstmmentioning
confidence: 99%
“…GRU has fewer trainable parameters because it does not have the output layer like LSTM. Within GRU, the information flow control component is called a gate, and GRU has two gates, namely a Reset Gate and an Update Gate (Yang & Guo, 2021). The Reset Gate determines how to combine the new input with past information.…”
Section: Grumentioning
confidence: 99%
See 1 more Smart Citation
“…Using the stock market and macroeconomic variables from 1999 to 2009, Yang and Guo establish a simultaneous equation model for the return of stock index and macroeconomic variables and empirically analyze the relationship between the return of the stock market and the fluctuation of macroeconomics. The results show that the stock investment return can be used as a leading indicator in the recovery stage of the economic cycle and the preprosperity and middle stages, that is, the upward stage of the economic cycle has a certain correlation with stock returns [13]. Kurihara uses the causality test method to empirically test the causal relationship between money supply, economic growth, wage costs, and inflation [14].…”
Section: Related Workmentioning
confidence: 99%