Working Paper: CEPR ID: DP17519
Authors: Gergely Buda; Vasco Carvalho; Stephen Hansen; Alvaro Ortiz; Tomasa Rodrigo; José V. RodrÃguez Mora
Abstract: This paper provides the first proof of concept that naturally occurring transaction data, arising from the decentralized activity of millions of economic agents, can be harnessed to produce national accounts-like objects. We deploy comprehensive transaction-level data and its associated metadata arising from the universe of Spanish retail accounts of Banco Bilbao Vizcaya Argentaria (BBVA). We organize the resulting 3 billion individual transactions by 1.8 million bank customers in a large and highly detailed representative consumption panel to show (i) that the aggregation of such data, once organized according to national accounting principles, can reproduce current official statistics on aggregate consumption in the national accounts with a high degree of precision and, as a result of the richness of transaction data, (ii) produce novel, highly detailed distributional accounts for consumption. Finally, exploiting the panel nature of our data, we (iii) offer a non-parametric analysis of individual consumption dynamics across the consumption distribution.
Keywords: national accounts; naturally occurring data; consumption; consumption inequality; consumption dynamics
JEL Codes: D30; E01; E21
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| aggregation of transaction-level data organized according to national accounting principles (E01) | reproduce current official statistics on aggregate consumption (E20) |
| methodology allows for the construction of novel distributional accounts for consumption (D39) | revealing larger consumption inequality than traditional surveys suggest (F61) |
| nonparametric analysis of individual consumption dynamics (D12) | identifying significant mean reversion in consumption growth and thick tails in the distribution of consumption changes (D15) |