Bruijn, NathanWijnhoven, FonsEffing, Robin2024-09-262024-09-262024-07-169788413962016https://riunet.upv.es/handle/10251/208678[EN] The forecasting field has been using the surge in big data and advanced computational capabilities. This article discusses the methodological issues of Google Trends (GT) data reliability and forecasting validity for youth unemployment forecasts. We demonstrate the problems with static GT forecasting procedures and show a 44% increase in forecasting accuracy by applying time-varying model respecification forecasting. 9Reconocimiento - No comercial - Compartir igual (by-nc-sa)Forecasting accuracyTime seriesRolling windowExpanding windowUnemploymentGoogle trendsParameter instabilityCapítulo de libro10.4995/CARMA2024.2024.17158Abierto