Abstract: From two professional news providers we retrieve news stories and earnings announcements of the S&P 100 constituents and 10 macro fundamentals, moreover we gather Google Trends of the assets. We create an extensive and innovative database, useful to analyze the link between news and asset price dynamics. We detect the sentiment of news stories using a dictionary of sentiment words and negations, and propose a set of more than 5K information-based variables that provide natural proxies of the information used by heterogeneous market players and of retail investors attention.We first shed light on the impact of information measures on daily realized volatility and select them by penalized regression; then, we use them to forecast volatility and obtain superior results with respect to models that omit them. Finally, we relate news with intraday jumps using penalized logistic regression.
Per motivi organizzativi si prega di conferma le presenza al seguente indirizzo: formazione@prometeia.com