Working Paper: NBER ID: w31315
Authors: Michael Cafarella; Gabriel Ehrlich; Tian Gao; John C. Haltiwanger; Matthew D. Shapiro; Laura Zhao
Abstract: This paper uses machine learning (ML) to estimate hedonic price indices at scale from item-level transaction and product characteristics. The procedure uses state-of-the-art approaches from hedonic econometrics and implements them with a neural network ML approach. Applying the methodology to Nielsen Retail Scanner data leads to a large hedonic adjustment to the Tornqvist index for food product groups: Cumulative food inflation over the period from 2007 through 2015 is reduced by half from 5.9% to 2.8% -- owing to quality adjustment. These results suggest that quality improvement via product turnover is important even in product groups that are not normally considered to feature rapid technological progress. The approach in the paper thus demonstrates the feasibility and importance of implementing hedonic adjustment at scale.
Keywords: Machine Learning; Hedonic Price Indices; Inflation Measurement
JEL Codes: C81; E31
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| machine learning methods (C45) | more accurate measure of inflation (E31) |
| quality improvement via product turnover (L15) | more accurate measure of inflation (E31) |
| traditional price indices (C43) | overstate inflation rates (E31) |
| traditional price indices (C43) | understate real output growth (O40) |
| machine learning methods (C45) | significant hedonic adjustment to the Tornqvist index (C43) |