Machine learning core inflation

Marco A. Acosta

Economics Letters, 2018, vol. 169, issue C, 47-50

Abstract: In this article a novel methodology for building core inflation measures is proposed based on the k-means clustering machine learning algorithm. This new methodology is explored using Mexican CPI data in the spirit of getting a clear signal and having good predictions of the inflationary process based on selecting items with low volatility and assigning them to clusters. The results show that the core inflation built captures better the inflation signal and also outperforms the short-term inflation forecasts obtained by the trimmed means method and the core inflation excluding food and energy.

Keywords: Machine learning; k-means algorithm; Core inflation (search for similar items in EconPapers)
JEL-codes: C43 E31 E37 (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0165176518301745
Full text for ScienceDirect subscribers only

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:eee:ecolet:v:169:y:2018:i:c:p:47-50

DOI: 10.1016/j.econlet.2018.05.001

Access Statistics for this article

Economics Letters is currently edited by Economics Letters Editorial Office

More articles in Economics Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().