Abstract:
This paper presents a forecasting exercise that assesses the predictive potential of a daily price index based on online prices. Prices are compiled using web scrapping services provided by the private company PriceStats in cooperation with a finance research corporation, State Street Global Markets. This online price index is tested as a predictor of the monthly core inflation rate in Argentina, known as "resto IPCBA" and published by the Statistics Office of the City of Buenos Aires. Mixed frequency regression models offer a convenient arrangement to accommodate variables sampled at different frequencies and hence many specifications are evaluated. Different classes of these models are found to produce a slight boost in out-of-sample predictive performance at immediate horizons when compared to benchmark näive models and estimators. Additionally, an analysis of intra-period forecasts, reveals a slight trend towards increased forecast accuracy as the daily variable approaches one full month for certain horizons.
