Constructing Consumer Sentiment Index for U.S. Using Google Searches

Abstract

We construct a consumer sentiment index for the U.S. using the popularity trends of selected Google searches. The final index consists of four components and is highly correlated with the Index of Consumer Sentiment from the University of Michigan and the Consumer Confidence Index from the Conference Board. Among the three sentiment indices, the Google search-based index (SBI) leads in time and predicts other indices. In terms of forecasting consumer spending, the SBI outperforms both the ICS and the CCI and provides independent information. For robustness, we use multiple measures of consumer spending and a range of statistical specifications. The finding is robust.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 37 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.