Macroeconomic news sentiment: Enhanced risk assessment for sovereign bond spreads
Christina Erlwein-Sayer explains how to enhance the modeling and forecasting of sovereign bond spreads by considering quantitative information gained from macroeconomic news sentiment, using a number of large news analytics datasets.
| Talk Title | Macroeconomic news sentiment: Enhanced risk assessment for sovereign bond spreads |
| Speakers | Christina Erlwein-Sayer (OptiRisk Systems) |
| Conference | Strata Data Conference |
| Conf Tag | Making Data Work |
| Location | London, United Kingdom |
| Date | May 22-24, 2018 |
| URL | Talk Page |
| Slides | Talk Slides |
| Video | |
Christina Erlwein-Sayer explains how to enhance the modeling and forecasting of sovereign bond spreads by considering quantitative information gained from macroeconomic news sentiment, using a number of large news analytics datasets. Christina then offers a demonstration of this model that investigates sovereign bonds spreads of five European countries. The prediction of spread changes is improved by incorporating news sentiment from relevant entities and macroeconomic topics. In particular, daily news sentiment series are created from sentiment scores as well as positive and negative news volume, and their effects on yield spreads and spread volatility are investigated. Christina conducts a rolling correlation analysis between sovereign bond spreads and accumulated sentiment series and analyzes changing correlation patterns over time, detecting market regimes through correlation series and exploring the impact of news sentiment on sovereign bonds in different market circumstances. Along the way, Christina shares best-suited external news variables for forecasts in an ARIMAX model setup. Error measures for forecasts of spread changes and volatility proxies are improved when sentiment is considered. These findings are then utilized to monitor sovereign bonds from European countries and detect changing risks through time.
