Sentiment Proxies: Computing Market Volatility
Macroeconomic announcements can have an influential effect on the price, and related volatility, of an object traded in financial markets. Modeling the impact of a relevant announcement on a specific commodity is of interest in building financial models of such objects. The announcements may generate false hopes or correctly indicate the ways in which the prices of objects may change. We describe a bootstrap model which is an attempt to analyse the impact of a publicly released oil inventory announcement on the price of oil futures contracts. A comparison with traditional econometric regression model is presented and we perturb the traditional models with: (a) a dummy time series that contains the dates on which the announcement is made, and (b) a sentiment time series that reflects the sentiment of the market. The sentiment time series is generated using natural language processing techniques.
KeywordsPrice Change Sentiment Analysis Future Contract Foreign Exchange Market Price Return
Unable to display preview. Download preview PDF.
- 3.Andersen, T.G., Bollerslev, T., et al.: Real-time price discovery in global stock, bond and foreign exchange markets. NBER Working Paper Series, No. 11312(2), pp. 251–277 (2007)Google Scholar
- 7.Efron, B., Tibshirani, R.: An introduction to the bootstrap. Chapman Hall (1993)Google Scholar
- 9.Payne, R.: Announcement effects and seasonality in the intra-day foreign exchange market. Discussion paper series, vol. 238. LSE Financial Markets Group (1996)Google Scholar
- 10.WPSR (Weekly Petroleum Status Report), http://www.eia.gov