IFS Seminar - Matt Shapiro (University of Michigan)

Abstract: This paper explores alternative methods for adjusting price indices for quality change at scale.  These methods can be applied to large-scale item-level transactions data that includes information on prices, quantities, and item attributes.  The hedonic methods can take into account the changing valuations of both observable and unobservable characteristics in the presence of product turnover.  The paper also considers demand-based approaches that take into account changing product quality from product turnover and changing appeal of continuing products. The paper provides evidence of substantial quality-adjustment in prices for a wide range of goods, including both high-tech consumer products and food products.
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.
Location: IFS conference centre