VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8001–8013, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8001 VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls Ramit Sawhney Netaji Subhas Institute of Technology ramits.co@nsit.net.in Piyush Khanna Delhi Technological University piyushkhanna bt2k17@dtu.ac.in Arshiya Aggarwal MIDAS, IIIT Delhi arshiya.dtu@gmail.com Taru Jain MIDAS, IIIT Delhi jaintaru@ieee.org Puneet Mathur University of Maryland, College Park puneetm@cs.umd.edu Rajiv Ratn Shah IIIT Delhi rajivratn@iiitd.ac.in Abstract Natural language processing has recently made stock movement forecasting and volatil- ity forecasting advances, leading to improved financial forecasting. Transcripts of compa- nies’ earnings calls are well studied for risk modeling, offering unique investment insight into stock performance. However, vocal cues in the speech of company executives present an underexplored rich source of natural lan- guage data for estimating financial risk. Ad- ditionally, most existing approaches ignore the correlations between stocks. Building on existing work, we introduce a neural model for stock volatility prediction that accounts for stock interdependence via graph convolu- tions while fusing verbal, vocal, and finan- cial features in a semi-supervised multi-task risk forecasting formulation. Our proposed model, VolTAGE, outperforms existing meth- ods demonstrating the effectiveness of multi- modal learning for volatility prediction. 1 Introduction Motivation Financial risk modeling is of great interest to capital market participants for making sound investment decisions. Stock volatility is a vi- tal indicator of a company’s risk profile (Poon and Granger, 2003; Yang et al., 2020). The stock mar- ket presents various opportunities that increasingly attract investors, who utilize the market’s poten- tial to generate profits, wherein stock volatility is a vital risk modeling factor. One underexplored, yet crucial event that leads to significant fluctua- tions in stock volatility, is the earnings conference call. These calls are held periodically by publicly traded companies’ executives to summarize and prognosticate company’s performance (Qin and Yang, 2019). Harnessing the interplay between the multimodal verbal and vocal cues in earnings calls can help better analyze the impact these calls may have on financial markets and forecast stock volatil- ity (Dichev and Tang, 2009; Yang et al., 2020). Challenges While stock trading presents unpar- alleled investment opportunities, accurately predict- ing the rise and fall of stock prices has numerous challenges (Campbell et al., 1997). Conventional research in finance revolves around using histor- ical stock data to develop statistical models and recurrent neural networks (RNNs) capable of fore- casting price trends (Kristjanpoller et al., 2014; Zheng et al., 2019). They are influenced by many factors ranging from public opinion to the move- ments of other related stocks (Malkiel, 2003). Re- cent advances in deep learning present a promis- ing prospect in multimodal stock forecasting by analyzing online news (Hu et al., 2018), and so- cial media (Guo et al., 2018) to learn latent pat- terns affecting stock prices (Jiang, 2020). How- ever, the challenging aspect in stock forecasting is that most existing work treats stock movements to be independent of each other, contrary to true market function (Diebold …

Content truncated to 500 words