Modelling Liquified Petroleum Gas Prices in Nigeria Using Machine Learning Models

Tayo P. Ogundunmade (1) , Adedayo A. Adepoju (2)
(1) University of Tlemcen, Algeria and Laboratory for Interdisciplinary Statistical Analysis(UI-LISA), Department of Statistics, University of Ibadan, Ibadan, Nigeria
(2) Department of Statistics, Faculty of Science, University of Ibadan, Ibadan, Nigeria
Fulltext View | Download


 The usage of Liquefied Petroleum Gas in households has been to increase in recent years. The energy used by households has proved difficult to forecast due to the nature of the independent variables. In recent years, deep learning models has been broadly utilized in the machine learning area to model time series data. Most noticeable is in the field of forecasting. In this work, Neural Network Autoregressive model (NNETAR), Naive forecasting and the Autoregressive Integrated Moving Average (ARIMA) models were used to model the price of Liquefied Petroleum Gas prices(LPG) of 37 states (including the FCT) in Nigeria, with input variables in the form of the price of refilling LPG for 12.5 kg from January 2016 to April 2019 covering a 1480 data points. The Mean Absolute Percentage Errors was used to measure the performance of the model. The result shows that Naive produced lower MAPE for more states compare to NNETAR and ARIMA models.

Article Details

How to Cite
T. P. Ogundunmade and A. A. Adepoju, “Modelling Liquified Petroleum Gas Prices in Nigeria Using Machine Learning Models”, Int. J. Data. Science., vol. 3, no. 2, pp. 93-100, Dec. 2022.


Afimia, E. O. (2019). Estimating Natural Gas Demand Elasticities in Nigeria. 2(4), 1–12.

Gould, C. F., & Urpelainen, J. (2018). LPG as a clean cooking fuel: Adoption, use, and impact in rural India. Energy Policy, 122(July), 395–408.

Hossein Hakimpoor, Tat Hon Huam, N. Khani and Mojgan Bahrami (2011): Marketing networking dimensions (Mnds) and Smes' Performance: A new conceptual model.Australian Journal of Basic and Applied Sciences 5(10):1528-1533.

Hyndman, R. J., & Khandakar, Y. (2008). Automatic time series forecasting: The forecast package for R.
Journal of Statistical Software, 27 (1), 1-22.

Tei, J., Marbuah, G., & Amoah, A. (2016). Energy demand in Ghana : A disaggregated analysis. 53, 924–935. Universities of Leeds , Sheffield and York. (2011).

Olubusoye, O. E. and Yaya, O. S. (2016). Time Series Analysis of Volatility in the Petroleum Markets: The Persistence, Asymmetry and Jumps in the Returns Series. OPEC Energy Review, 42(3): 235-262

Tayo P. Ogundunmade and A. A. Adepoju, “The Performance of Artificial Neural Network Using Heterogeneous Transfer Functions”, Int. J. Data. Science., vol. 2, no. 2, pp. 92-103, Dec. 2021.

Yaya, O.S., Gil-Alana, L.A. and Carcel, H. (2015). Testing Fractional Persistence and Non-linearities in the Natural Gas Market: An Application of Non-linear Deterministic Terms based on Chebyshev Polynomials in Time. Energy Economics, 52 (A): 240-245. (Elsevier USA).