Economics at your fingertips  

Forecasting inflation using machine learning techniques

Musa Nakorji and Umaru Aminu

The Review of Finance and Banking, 2022, vol. 14, issue 1, 45-55

Abstract: Inflation forecasting is key in achieving the Central Bank mandate of price stability the world over. Different traditional methods were used to forecast inflation with little or no attention given to the area of forecasting the inflation rate in Nigeria using machine learning techniques. Data was sourced from CBN statistical bulletin (2021) on monthly basis. The study found that ridge regression and Artificial Neural Networks are the best in forecasting inflation in Nigeria when compared with the LASSO, elastic net, and PLS. The study further reveals that the major drivers of headline inflation in Nigeria were food inflation, core inflation, prime lending rate, maximum lending rate, and the inter-bank rate. The study recommends that ridge regression and Artificial Neural Network machine learning techniques be used in forecasting the inflation rate in Nigeria. Also, recommended is the need for the monetary authorities to focus more on ways to improve food production by improving security.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc

Downloads: (external link) Full text (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:

Access Statistics for this article

The Review of Finance and Banking is currently edited by Victor Dragota; Bogdan Negrea

More articles in The Review of Finance and Banking from Academia de Studii Economice din Bucuresti, Romania / Facultatea de Finante, Asigurari, Banci si Burse de Valori / Catedra de Finante Strada Mihai Eminescu nr.13-15, sector 1, Bucuresti, Romania. Contact information at EDIRC.
Bibliographic data for series maintained by Tatu Lucian ().

Page updated 2024-04-09
Handle: RePEc:rfb:journl:v:14:y:2022:i:1:p:45-55