arbiter
JournalsAccount

Improving disaggregated short-term food inflation forecasts with webscraped data

Christian Beer et al.

International Journal of Forecasting2026https://doi.org/10.1016/j.ijforecast.2026.02.003article
AJG 3ABDC A
Weight
0.50

Abstract

Recent studies suggest that webscraped price data can enhance the timeliness and accuracy of inflation nowcasts. In a forecasting competition against univariate time series benchmarks, we evaluate nowcasts and short-horizon forecasts using daily price quotes for Austria. Our findings indicate that webscraped data deliver accurate nowcasts several weeks earlier than official releases, because they enable the production of reliable estimates early in the reference month. Additionally, we demonstrate that nowcasts remain robust to structural breaks in food price dynamics. To our knowledge, this study is the first to examine whether webscraped nowcasts can improve disaggregated short-term forecasts up to one quarter ahead. Although direct forecasts at higher levels of aggregation are slightly more accurate, indirect forecasts derived from disaggregated data provide superior insights into the underlying dynamics of sub-components. These findings have implications for policymakers aiming to develop an effective system for real-time monitoring of inflation dynamics at a granular level.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1016/j.ijforecast.2026.02.003

Or copy a formatted citation

@article{christian2026,
  title        = {{Improving disaggregated short-term food inflation forecasts with webscraped data}},
  author       = {Christian Beer et al.},
  journal      = {International Journal of Forecasting},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1016/j.ijforecast.2026.02.003},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Improving disaggregated short-term food inflation forecasts with webscraped data

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.