ON COMPARATIVE STUDY OF NEURAL NETWORK AND MARKOV-SWITCHING  MODELS FOR INFLATION FORECASTING

Mutairu Oyewale Akintunde; Nkiru Obioma Eriobu; Akinyemi Samuel Ogunleke; Basirat Omotola Adetona

Mutairu Oyewale Akintunde Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.
Nkiru Obioma Eriobu Department Of Statistics, Nnamdi Azikwe University, Anambra State.
Akinyemi Samuel Ogunleke IT- Business and Advanced Analytics Department. New Brunswick Community College, Saint John, NB, Canada
Basirat Omotola Adetona Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.

Keywords: Artificial Neural Network (ANN), Markov-Switching Model (MSM), Inflation, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Theil’s U-statistic.

Abstract

This study examines the effectiveness of forecasting inflation in Nigeria over the period 2000 to
2024 using Artificial Neural Networks (ANN) and Markov-Switching Models (MSM). It
assesses the ability of each model to capture nonlinear dynamics and structural shifts in inflation
behaviour during the study period. Monthly inflation data obtained from the National Bureau of
Statistics, the official data source, were analysed. Model performance was evaluated using
standard forecast accuracy measures, including the Mean Absolute Error (MAE), Root Mean
Square Error (RMSE), and Theil’s U-statistic. The results show that the ANN model delivers
higher forecasting accuracy by effectively capturing complex nonlinear relationships in the data.
In contrast, the MSM performs better in identifying transitions between low- and high-inflation
regimes, thereby providing useful insights into the structural behaviour of the economy. Overall,
the findings suggest that integrating machine learning techniques with regime-switching models
can enhance forecast accuracy and provide valuable support for monetary and fiscal policy
formulation in Nigeria.

Author Biographies

Mutairu Oyewale Akintunde, Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.

Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.

Nkiru Obioma Eriobu, Department Of Statistics, Nnamdi Azikwe University, Anambra State.

Department Of Statistics, Nnamdi Azikwe University, Anambra State.

Akinyemi Samuel Ogunleke, IT- Business and Advanced Analytics Department. New Brunswick Community College, Saint John, NB, Canada

IT- Business and Advanced Analytics Department. New Brunswick Community College, Saint
John, NB, Canada

Basirat Omotola Adetona, Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.

Department Of Statistics, Federal University Of Agriculture, Abeokuta, Ogun State.