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

Luca Barbaglia,Sebastiano Manzan,Sergio Consoli

doi:10.1007/978-3-030-66981-2_11

Abstract

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.

Highlights

Monitoring the current and forecasting the future state of the economy is of fundamental importance for governments, international organizations, and central banks
We report on some preliminary findings on the use-case application of DeepAR along the Word Embedding extracted by a GloVe pre-trained model from United States (US) news ranging from January 1982 to September 2019, with the goal of predicting the future values of the US 10-Year Treasury Constant Maturity Minus 3-Month Treasury Constant Maturity (T10Y3M) time series given its past values
We show our preliminary findings on the application of DeepAR to the forecasting of the T10Y3M time series, augmented by the extracted Word Embedding from the US economic news

Summary

Introduction

Monitoring the current and forecasting the future state of the economy is of fundamental importance for governments, international organizations, and central banks. They rely on economic indicators produced by statistical agencies that are released at low frequencies (e.g., monthly or quarterly), with considerable delays, and that are often subject to substantial revisions. Greater interdependence means that the current and future conditions of a market are linked to instabilities and extreme events originated abroad All these factors make the economic forecasting task extremely difficult, both in the short and in the medium-long run. A more direct approach is to use recurrent connections that connect the neural networks hidden units back to themselves with a time delay This is the principle at the base of Recurrent Neural Networks (RNNs) [15,21], which are NNs designed to handle sequential data that arise in applications such as time series, natural language processing and speech recognition. For example, the authors in [16] developed a multi-task RNN with high-order Markov random fields to predict stock price movement direction based upon a single stock’s historical records together with its correlated stocks

Objectives

Results

Conclusion