Information Extraction From the GDELT Database to Analyse EU Sovereign Bond Markets

In this contribution we provide an overview of a currently on-going project related to the development of a methodology for building economic and financial indicators capturing investor’s emotions and topics popularity which are useful to analyse the sovereign bond markets of countries in the EU.These alternative indicators are obtained from the Global Data on Events, Location, and Tone (GDELT) database, which is a real-time, open-source, large-scale repository of global human society for open research which monitors worlds broadcast, print, and web news, creating a free open platform for computing on the entire world’s media. After providing an overview of the method under development, some preliminary findings related to the use case of Italy are also given. The use case reveals initial good performance of our methodology for the forecasting of the Italian sovereign bond market using the information extracted from GDELT and a deep Long Short-Term Memory Network opportunely trained and validated with a rolling window approach to best accounting for non-linearities in the data.

Exploring the Predictive Power of News and Neural Machine Learning Models for Economic Forecasting

Forecasting economic and financial variables is a challenging task for several reasons, such as the low signal-to-noise ratio, regime changes, and the effect of volatility among others. A recent trend is to extract information from news as an additional source to forecast economic activity and financial variables. The goal is to evaluate if news can improve forecasts from standard methods that usually are not well-specified and have poor out-of-sample performance. In a currently on-going project, our goal is to combine a richer information set that includes news with a state-of-the-art machine learning model. In particular, we leverage on two recent advances in Data Science, specifically on Word Embedding and Deep Learning models, which have recently attracted extensive attention in many scientific fields. We believe that by combining the two methodologies, effective solutions can be built to improve the prediction accuracy for economic and financial time series. In this preliminary contribution, we provide an overview of the methodology under development and some initial empirical findings. The forecasting model is based on DeepAR, an auto-regressive probabilistic Recurrent Neural Network model, that is combined with GloVe Word Embeddings extracted from economic news. The target variable is the spread between the US 10-Year Treasury Constant Maturity and the 3-Month Treasury Constant Maturity (T10Y3M). The DeepAR model is trained on a large number of related GloVe Word Embedding time series, and employed to produce point and density forecasts.