Andrei Velichko, Imen Mahmoud · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28563 · open-access PDF
La actividad de búsqueda en línea se utiliza ampliamente como un rastro digital de información que se busca durante las epidemias, pero su valor predictivo a menudo se reduce a una correlación, un atraso seleccionado, o una única puntuación de error de predicción. Examinamos ocho pares predefinidos de Google Trends-COVID-19 en ambas direcciones utilizando las predicciones de LightGBM correspondientes sobre ventanas de 400 días y horizontes de 1-14 días. El log-RMSE se combina con la entropía de distribución de errores de predicción (FEDE), que captura los cambios dependentes del horizonte en la distribución de errores firmados.
Machine translation (Meta M2M100); the English original follows.
Online search activity is widely used as a digital trace of information seeking during epidemics, but its predictive value is often reduced to correlation, a selected lag, or a single forecast-error score. We examine eight pre-specified Google Trends-COVID-19 pairs in both directions using matched LightGBM forecasts over rolling 400-day windows and horizons of 1-14 days. Log-RMSE gain is combined with forecast-error distribution entropy (FEDE), which captures horizon-dependent changes in the signed error distribution. The resulting directional predictive signature comprises response class, RMS
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28563, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange