Realised Volatility Forecasting: Machine Learning via Financial Word Embedding

Abstract

We develop FinText, a novel, state-of-the-art, financial word embedding from Dow Jones Newswires Text News Feed Database. Incorporating this word embedding in a machine learning model produces a substantial increase in volatility forecasting performance on days with volatility jumps for 23 NASDAQ stocks from 27 July 2007 to 18 November 2016. A simple ensemble model, combining our word embedding and another machine learning model that uses limit order book data, provides the best forecasting performance for both normal and jump volatility days. Finally, we use Integrated Gradients and SHAP (SHapley Additive exPlanations) to make the results more 'explainable' and the model comparisons more transparent.

Deepvol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions

“…This has given rise to an increasing usage of volatility conditional portfolios (Harvey et al 2018), with different studies reporting an overall gain in their Sharpe ratio (Moreira and Muir 2017), as well as a reduction of the likelihood of observing extreme heavy-tailed returns in volatility scaled portfolios (Harvey et al 2018). The development of volatility forecasting models has consequently attracted broad research efforts, but most of the models used by practitioners are based on classic methodologies such as the GARCH model (Bollerslev poller 2020), Graph Neural Networks (GNN) (Chen and Robert 2021), Transformer models (Ramos-Pérez, Alonso-González, and Núñez-Velázquez 2021), and NLP-based word embedding techniques (Rahimikia and Poon 2020;Rahimikia, Zohren, and Poon 2021). Furthermore, models combining traditional volatility forecasting methods with deep-learning techniques can be found in the literature (Kim and Won 2018;Mademlis and Dritsakis 2021), as well as other approaches using DNN as calibration methods for implying volatility surfaces (Horvath, Muguruza, and Tomas 2019), proving how neural network-based approaches work as complex pricing function approximators.…”