Nowcasting economic activity with electronic payments data: A predictive modeling approach

Borradores de Economia
Número: 
1037
Publicado: 
Clasificación JEL: 
E27, C53, C45

Lo más reciente

Julián Alonso Cárdenas-Cárdenas, Deicy Johana Cristiano-Botia, Eliana Rocío González-Molano, Carlos Alfonso Huertas-Campos
Luis E. Arango, Juan José Ospina-Tejeiro, Fernando Arias-Rodríguez, Oscar Iván Ávila-Montealegre, Jaime Andrés Collazos-Rodríguez, Diana M. Cortázar Gómez, Juan Pablo Cote-Barón, Julio Escobar-Potes, Aarón Levi Garavito-Acosta, Franky Juliano Galeano-Ramírez, Eliana Rocío González-Molano, Maria Camila Gomez Cardona, Anderson Grajales, David Camilo López-Valenzuela, Wilmer Martinez-Rivera, Nicolás Martínez-Cortés, Rocío Clara Alexandra Mora-Quiñones, Sara Naranjo-Saldarriaga, Antonio Orozco, Daniel Parra-Amado, Julián Pérez-Amaya, José Pulido, Karen L. Pulido-Mahecha, Carolina Ramírez-Rodríguez, Sergio Restrepo Ángel, José Vicente Romero-Chamorro, Nicol Valeria Rodríguez-Rodríguez, Norberto Rodríguez-Niño, Diego Hernán Rodríguez-Hernández, Carlos D. Rojas-Martínez, Johana Andrea Sanabria-Domínguez, Diego Vásquez-Escobar
Luis Armando Galvis-Aponte, Adriana Isabel Ortega-Arrieta, Adriana Marcela Rivera-Zárate

Economic activity nowcasting (i.e. making current-period estimates) is convenient because most traditional measures of economic activity come with substantial lags. We aim at nowcasting ISE, a short-term economic activity indicator in Colombia. Inputs are ISE’s lags and a dataset of payments made with electronic transfers and cheques among individuals, firms, and the central government. Under a predictive modeling approach, we employ a nonlinear autoregressive exogenous neural network model. Results suggest that our choice of inputs and predictive method enable us to nowcast economic activity with fair accuracy.

Also, we validate that electronic payments data significantly reduces the nowcast error of a benchmark non-linear autoregressive neural network model.

Nowcasting economic activity from electronic payment instruments data not only contributes to agents’ decision making and economic modeling, but also supports new research paths on how to use retail payments data for appending current models.