Nowcasting commodity price of a developing country based on social web data

Abstract

Up-to-date daily information on food prices is invaluable to help policymakers and development organizations address food security problems and improve public welfare. With growing Internet connectivity in developing countries, this study analyses the possible use of large-scale online data to provide updates on the food security landscape. Through a case study of Indonesia, we develop an integrated approach to nowcast daily food prices for four types of food commodities that are essential in the region: beef, chicken, onion and chilli. Data analysis shows that suggested algorithm outperforms traditional nowcast methods and baselines in terms of prediction performance metrics.