Analyzing VAT pass-through in Spain using web-scraped supermarket data and machine learning

On December 27, 2022, the Spanish government announced a temporary value added tax (VAT) rate reduction for selected products. VAT rates were cut on January 1, 2023. Initially, the VAT was expected to go back to their previous level six months later, but several waivers led this policy to last for 21–24 months, where the VAT returned to its original level in two phases. We study the pass-through of the temporary VAT rate changes covering the daily prices of roughly 21.000 food products sold online in a Spanish supermarket. We achieve this by utilizing a dataset obtained by web-scraping and employing machine-learning methods to classify each product into a COICOP5 category. To identify the causal price effects, we compare the evolution of prices for treated items (that is, subject to the tax policy) against a control group (food items out of the policy’s scope). Our findings indicate that, at the supermarket level, the pass-through was almost complete after one week. In using product characteristics, we notice differences in the rate of pass-through and in pricing strategy in the subsequent weeks.