## Housing Boom and Headline Inflation: Insights from Machine Learning

_IMF Working Papers, July 28, 2022_

## Source details

**Canonical URL:** [Housing Boom and Headline Inflation: Insights from Machine Learning](https://www.imf.org/en/publications/wp/issues/2022/07/28/housing-boom-and-headline-inflation-insights-from-machine-learning-521324)

## Other formats

- [Markdown version](/en/publications/wp/issues/2022/07/28/housing-boom-and-headline-inflation-insights-from-machine-learning-521324/index.md)
- [Structured JSON version](/en/publications/wp/issues/2022/07/28/housing-boom-and-headline-inflation-insights-from-machine-learning-521324/index.json)
- [Bundle manifest](/en/publications/wp/issues/2022/07/28/housing-boom-and-headline-inflation-insights-from-machine-learning-521324/bundle-manifest.json)

## Bibliographic details
- Authors: Yang Liu, Di Yang, Yunhui Zhao
- Published: July 28, 2022
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9798400218095.001

---

### Summary and context
- Title: Housing Boom and Headline Inflation: Insights from Machine Learning
- Authors: Yang Liu, Di Yang, Yunhui Zhao
- Date: July 28, 2022
- Publication: IMF Working Papers, Working Paper No. 2022/151
- Pages: 45
- Volume: 2022
- Issue: 151
- DOI: https://doi.org/10.5089/9798400218095.001
- ISBN: 9798400218095
- ISSN: 1018-5941
- Subject tags: Consumer price indexes, Economic forecasting, Housing, Housing prices, Inflation, National accounts, Prices

### Stylized facts on housing and inflation
- Inflation rose during the pandemic against supply chain disruptions and a multi-year boom in global owner-occupied house prices.
- House prices are presented as a leading indicator of headline inflation in the U.S. and eight other major economies with fast-rising house prices.
- The analysis focuses on two housing components of headline inflation: rent and owner-occupied housing cost.

### Forecasting approach and methodological insights
- The paper applies machine learning methods to forecast inflation in the two housing components (rent and owner-occupied housing cost) of headline inflation.
- For the vast majority of countries analyzed, machine-learning models outperform the VAR model.
- The methodological finding suggests potential value for incorporating machine-learning models into inflation forecasting.

### Key empirical findings and inferences
- Results suggest that for most of the countries in the sample:
  - The housing components could have a relatively large and sustained contribution to headline inflation.
  - Inflation is just starting to reflect the higher house prices, implying further inflationary impact may materialize as housing cost measures respond.

### Policy-relevant implications (as conveyed in the source)
- Monitoring owner-occupied house prices and housing cost components (rent and owner-occupied housing cost) is important for understanding near-term headline inflation dynamics in countries experiencing housing booms.
- Incorporating machine-learning forecasting models may improve inflation forecasts relative to VAR models for these housing-related inflation components.

*IMF Working Paper No. 2022/151, July 28, 2022*

---

## Content in this bundle

- **Working Paper**
  - [Working Paper (Markdown version)](/-/media/files/publications/wp/2022/english/wpiea2022151-print-pdf.pdf.md){rel="alternate" type="text/markdown"}
  - [Working Paper (PDF)](/-/media/files/publications/wp/2022/english/wpiea2022151-print-pdf.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/wp/issues/2022/07/28/housing-boom-and-headline-inflation-insights-from-machine-learning-521324_