Evaluating Time Series and Machine Learning Approaches for Forecasting Inflation in Nigeria
DOI:
https://doi.org/10.33003/fjorae.2025.0201.04Keywords:
Inflation Forecasting,, Time Series Analysis,, Machine Learning,, Hybrid Modeling,, Economic Prediction.Abstract
Inflation forecasting is crucial for economic planning, policy formulation, and financial decision-making. This study evaluates the performance of various forecasting models for inflation in Nigeria, including Autoregressive Integrated Moving Average (ARIMA), Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). These models were selected for their proven effectiveness in macroeconomic forecasting and their ability to capture both linear and non-linear trends. Monthly inflation data from 2000 to 2024 were obtained from the Central Bank of Nigeria (CBN) and the National Bureau of Statistics (NBS), enabling a comprehensive analysis of long-term inflation trends. The performance of the models was assessed using Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). Results indicate that standalone ARIMA performed poorly, with high error metrics (MSE: 13.35, RMSE: 11.42, MAPE: 37.74%), highlighting its limitations in capturing non-linear inflation patterns. In contrast, machine learning models, particularly ANN (MSE: 1.758, RMSE: 1.694, MAPE: 0.059%), significantly outperformed ARIMA. Hybrid models demonstrated superior performance, with ARIMA-ANN achieving the best results (MSE: 0.611, RMSE: 0.755, MAPE: 0.054%), underscoring the effectiveness of combining statistical and machine learning techniques. While hybrid models, particularly ARIMA-ANN, offer a robust framework for inflation forecasting, their computational complexity and risk of overfitting require careful optimization. The study also assesses model efficiency to ensure practical applicability for economic decision-making. The findings provide policymakers with a reliable forecasting tool to mitigate inflation volatility, optimize monetary policy, and enhance economic stability. This research concludes that hybrid modeling, despite its complexity, provides more accurate and reliable predictive insights, making it a valuable tool for economic planning and policy formulation.
References
Adebiyi, M. A., Adenuga, A. O., Olusegun, T. S., & Mbutor, O. O. (2022). Big Data and Inflation Forecasting in Nigeria: a text mining application. Economic and Financial Review, 60(1), 1-23.
Adelekan, O. G., Abiola, O. H., & Constance, A. U. (2020). Modelling and forecasting inflation rate in Nigeria using ARIMA models. KASU Journal of Mathematical Sciences (KJMS, 1(2), 127-143.
Alfa, M. S., & Dauda, S. (2024). Time Series Analysis: A Model Solution for Addressing Nigeria's Economic Challenges. African Journal of Management and Business Research, 17(1), 178-205.
Araujo, G. S., & Gaglianone, W. P. (2023). Machine learning methods for inflation forecasting in Brazil: New contenders versus classical models. Latin American Journal of Central Banking, 4(2), 100087.
Aras, S., & Lisboa, P. J. (2022). Explainable inflation forecasts by machine learning models. Expert Systems with Applications, 207, 117982.
Awopegba, O. E., & Awe, O. O. (2024). Re-examining inflation and its drivers in Nigeria: A machine learning approach. In Sustainable Statistical and Data Science Methods and Practices: Reports from LISA 2020 Global Network, Ghana, 2022 (pp. 57-78). Cham: Springer Nature Switzerland.
Bandara, W. M. S., & De Mel, W. A. R. (2023). Evaluating the Predictive Performance of Monthly Inflation Rates in Sri Lanka using the Hybrid Model (HB). Asian Journal of Probability and Statistics, 25(4), 1-14.
Baybuza, I. (2018). Inflation forecasting using machine learning methods. Russian Journal of Money and Finance, 77(4), 42-59.
Dinh, D. (2020). Impulse response of inflation to economic growth dynamics: VAR model analysis. The Journal of Asian Finance, Economics and Business, 7(9), 10-13106.
Doguwa, S. I., & Alade, S. O. (2013). Short-term inflation forecasting models for Nigeria. CBN Journal of Applied Statistics, 4(3), 1-29.
Ekpeyong, P. (2023). Analysis of the dynamic of inflation process in Nigeria: An application of GARCH modelling.
Hamza, N. (2021). Modeling and Forecasting Inflation in Nigeria using Autoregressive Integrated Moving Average Technique. Gusau International Journal of Management and Social Sciences, Federal University, Gusau, 4(1).
Ibekwe, U., Mesike, G., & Ashogbon, M. (2023). Modelling Consumer Price Index Dynamics In Nigeria Using Decision Tree and Random Forest Machine Learning Algorithms. Unilag Journal of Business, 9(1), 114-129.
Ibrahim, A., & SO, O. (2020). ARIMA modeling and forecasting of consumer price index (CPI) in Nigeria. Mathematical Association of Nigeria (MAN), 47(1), 323.
Jagero, B. A., Mageto, T., & Mwalili, S. (2023). Modelling and Forecasting Inflation Rates in Kenya Using ARIMA-ANN Hybrid Model. American Journal of Neural Networks and Applications, 9(1), 8-17.
John, C., Izuchukwu, O. P., & Theresa, A. C. (2023). Application of Factor Analysis in the Modelling of Inflation Rate in Nigeria. Communication in Physical Sciences, 10(2).
Marpaung, G. N., Soesilowati, E., Rahman, Y. A., Tegar, Y. D., & Yuliani, R. (2022). Forecasting the Inflation Rate in Central Java Using ARIMA Model. Efficient: Indonesian Journal of Development Economics, 5(2), 163-173.
Nakorji, M., & Aminu, U. (2022). Forecasting inflation using machine learning techniques. Review of Finance and Banking, 14(1), 45-55.
Nkemnole, E. B., Wulu, J. T., & Osubu, I. (2024). Application of K-Nearest Neighbours and Long-Short-Term Memory Models using Hidden Markov Model to Predict Inflation Rate and Transition Patterns in Nigeria. Journal of Applied Sciences and Environmental Management, 28(6), 1913-1925.
Nyoni, T., & Nathaniel, S. P. (2018). Modeling rates of inflation in Nigeria: An application of ARMA, ARIMA and GARCH models.
Olajide, J. T., Ayansola, O. A., Odusina, M. T., & Oyenuga, I. F. (2012). Forecasting the Inflation Rate in Nigeria: Box Jenkins Approach. IOSR Journal of Mathematics (IOSR-JM), 3(5), 15-19.
Olalude, G. A., Olayinka, H. A., & Ankeli, U. C. (2020). Modelling and forecasting inflation rate in Nigeria using ARIMA models.
Oloko, T. F., Ogbonna, A. E., Adedeji, A. A., & Lakhani, N. (2021). Oil price shocks and inflation rate persistence: A Fractional Cointegration VAR approach. Economic Analysis and Policy, 70, 259-275.
Oyewale, A. M., Kasali, A. O., Phazamile, K., Abiodun, M. V., & Adeyinka, A. I. (2019). Forecasting Inflation Rates Using Artificial Neural Networks. International Journal of Statistics and Applications, 9(6), 201-207.
Peirano, R., Kristjanpoller, W., & Minutolo, M. C. (2021). Forecasting inflation in Latin American countries using a SARIMA–LSTM combination. Soft Computing, 25(16), 10851-10862.
Plas, J. D. C. (2023). Dutch Inflation Rate Forecasting Performance of Econometric and Neural Network Models (Master's thesis, University of Twente).
Rodríguez-Vargas, A. (2020). Forecasting Costa Rican inflation with machine learning methods. Latin American Journal of Central Banking, 1(1-4), 100012.
Šestanović, T., & Arnerić, J. (2021). Can recurrent neural networks predict inflation in euro zone as good as professional forecasters? Mathematics, 9(19), 2486.
Uko, A. K., & Nkoro, E. (2012). Inflation forecasts with ARIMA, vector autoregressive and error correction models in Nigeria. European Journal of Economics, Finance and Administrative Science, 50, 71-87.
Xavier, A. L., Fernandes, B. J., & de Oliveira, J. F. (2023, October). Hybrid Model and Ensemble for Inflation Forecasting: A Machine Learning Approach. In 2023 IEEE Latin American Conference on Computational Intelligence (LA-CCI) (pp. 1-6). IEEE.
