BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AMSE//Event Calendar//FR
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:event-13342@www.amse-aixmarseille.fr
DTSTAMP:20261122T130929Z
CREATED:20261122T130929Z
LAST-MODIFIED:20261122T130929Z
STATUS:CONFIRMED
SEQUENCE:0
SUMMARY:PhD seminar - Ulrich Aiounou
DTSTART:20261215T130000Z
DTEND:20261215T141500Z
DESCRIPTION:This paper examines whether news sentiment provides additional 
 predictive information for cryptocurrency returns and volatility beyond tha
 t contained in market variables. I use asset-specific news headlines collec
 ted from GDELT to construct two daily sentiment measures based on a financi
 al lexicon and FinBERT. The analysis covers Bitcoin\, Ether\, Solana\, and 
 XRP\, with multiple forecast horizons. Seven forecasting models are conside
 red\, including linear regressions\, tree-based methods\, and a neural netw
 ork. Forecasting performance is evaluated using an expanding-window approac
 h\, with RMSE comparisons and the Clark-West test. I consider both a common
  sample and asset-native samples to examine the sensitivity of the results 
 to the sample design. The analysis also examines whether the predictive con
 tribution of sentiment differs between high- and low-volatility market cond
 itions. The results indicate that news sentiment provides more favorable im
 provements for volatility forecasting than for returns. Statistically suppo
 rted return gains are relatively limited and rarely persist across the two 
 sample designs. In contrast\, several volatility forecasts benefit from sen
 timent information\, with the largest improvements generally obtained using
  Multilayer Perceptron (MLP)\, particularly for XRP. However\, some of thes
 e gains weaken or reverse when different sample periods are considered. The
  results also show that improvements occur under different market volatilit
 y conditions\, without a consistent advantage for either regime.\\n\\nConta
 ct: Sullivan Hué - sullivan.hue[at]univ-amu.frMichel Lubrano - michel.lubr
 ano[at]univ-amu.fr\n\nPlus d'informations: https://www.amse-aixmarseille.fr
 /fr/evenements/ulrich-aiounou-1
LOCATION:Îlot Bernard du Bois
URL;VALUE=URI:https://www.amse-aixmarseille.fr/fr/evenements/ulrich-aiounou-1
CONTACT:Sullivan Hué - sullivan.hue[at]univ-amu.frMichel Lubrano - michel.
 lubrano[at]univ-amu.fr
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR
