Modélisations Univariées de l’Inflation Mensuelle à Madagascar: l’Atout du Modèle LSTM, un Réseau de Neurones Récurrents

Anjara Lalaina Jocelyn Rakotoarisoa ()
Additional contact information
Anjara Lalaina Jocelyn Rakotoarisoa: Université de Toamasina

Post-Print from HAL

Abstract: This study focuses on univariate modeling and forecasting of monthly inflation in Madagascar, aiming to provide an analytical framework for price fluctuations in the country. By incorporating recurrent neural networks, specifically the LSTM model, the study seeks to enhance the accuracy of monthly inflation forecasts. Compared to traditional univariate models, such as SARIMA and exponential smoothing techniques, the LSTM proves to be more effective and resilient in capturing the complex inflation dynamics unique to Madagascar.

Keywords: LSTM; Neural Network; RNN; Inflation; Madagascar; Prix; SARIMA; lissage exponentiel (search for similar items in EconPapers)
Date: 2024-11-05
Note: View the original document on HAL open archive server: https://hal.science/hal-04766563v1
References: View references in EconPapers View complete reference list from CitEc
Citations:

Published in 2024

Downloads: (external link)
https://hal.science/hal-04766563v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04766563

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().