Realised Volatility Forecasting: Machine Learning via Financial Word Embedding

Abstract

We examine whether financial news can improve realised volatility forecasting using a parsimonious NLP-based framework that incorporates specialised financial word embeddings alongside general-purpose alternatives. News-only forecasts contain useful predictive information but generally do not outperform strong volatility-history benchmarks. Crucially, combining stock-related news forecasts with a strong volatility-history benchmark lowers forecast losses for several specifications and increases realised utility, providing evidence consistent with forecast complementarity. Performance varies across news types, embedding representations, and volatility regimes. SHAP attributions associate forecast variation with economically interpretable firm-specific and macroeconomic news themes.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Natural Language Processing (almost) from Scratch
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
• SHAP values for Explaining CNN-based Text Classification Models
• Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
• Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units