Sources and Types of Big Data for Macroeconomic Forecasting

Philip Garboden, Working Papers

RESEARCH PAPERS ARE PRELIMINARY MATERIALS CIRCULATED TO STIMULATE DISCUSSION AND CRITICAL COMMENT. THE VIEWS EXPRESSED ARE THOSE OF THE INDIVIDUAL AUTHORS. WHILE RESEARCH PAPERS BENEFIT FROM ACTIVE UHERO DISCUSSION, THEY HAVE NOT UNDERGONE FORMAL ACADEMIC PEER REVIEW.

This chapter considers the types of Big Data that have proven useful for macroeconomic forecasting. It first presents the various definitions of Big Data, proposing one we believe is most useful for forecasting. The literature on both the opportunities and challenges of Big Data are presented. It then proposes a taxonomy of the types of Big Data: 1) Financial Market Data; 2) E-Commerce and Credit Cards; 3) Mobile Phones; 4) Search; 5) Social Media Data; 6) Textual Data; 7) Sensors, and The Internet of Things; 8) Transportation Data; 9) Other Administrative Data. Noteworthy studies are described throughout.