Forecasting Inflation in Iran by Applying Maching Learning Algorithms to PPP Lag

Tal Boger
Additional contact information
Tal Boger: The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise

No 126, Studies in Applied Economics from The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise

Abstract: Purchasing Power Parity (PPP) relates the prices of two countries by their exchange rates. Several economists use PPP to measure inflation in the absence of official and accurate government reports. In the case of Iran, the government’s official inflation figures are significantly lower than what one would expect given their economic troubles; therefore, we apply PPP to measure inflation in Iran. Because of its volatility in the short-run, PPP is often used as a long-run economic indicator. The main cause for this is that PPP is a leading indicator, creating short-term inaccuracies. However, using machine learning algorithms, we forecast both the time until there is zero PPP lag (i.e. the official and implied inflation rates are equal) and the difference between the official and implied inflation rate (allowing us to predict official inflation rates) for Iran with minimal volatility. This allows us to use PPP accurately over both the short- and long-run.

Keywords: Keywords: Purchasing Power Parity (PPP); Iranian inflation; Machine learning; Support vector machine; Random forest; k-nearest neighbors; Neural network (search for similar items in EconPapers)
Pages: 24 pages
Date: 2018-09
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://sites.krieger.jhu.edu/iae/files/2018/09/Boger-Iran-ML-Inflation.pdf 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: https://EconPapers.repec.org/RePEc:ris:jhisae:0126

Access Statistics for this paper

More papers in Studies in Applied Economics from The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise Contact information at EDIRC.
Bibliographic data for series maintained by Steve H. Hanke ().