Abstract
Volatility prediction is complex due to the stock market’s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and risk, but ignores the rich acoustic features in the company executives’ speech. Recently, new multimodal approaches that leverage the verbal and vocal cues of speakers in financial disclosures significantly outperform previous state-of-the-art approaches demonstrating the benefits of multimodality and speech. However, the financial realm is still plagued with a severe underrepresentation of various communities spanning diverse demographics, gender, and native speech. While multimodal models are better risk forecasters, it is imperative to also investigate the potential bias that these models may learn from the speech signals of company executives. In this work, we present the first study to discover the gender bias in multimodal volatility prediction due to gender-sensitive audio features and fewer female executives in earnings calls of one of the world’s biggest stock indexes, the S&P 500 index. We quantitatively analyze bias as error disparity and investigate the sources of this bias. Our results suggest that multimodal neural financial models accentuate gender-based stereotypes.
Highlights
Why Study Bias?Bias in Finance Public financial data is impacting virtually every aspect of investment decision making (Pericet al., 2016; Brynjolfsson et al, 2011).Prior research shows that NLP methods leveraging social media (Sawhney et al, 2020a), news (Du and Tanaka-Ishii, 2020), and earning calls (Wang and Hua, 2014) can accurately forecast financial risk
Speech in earnings calls (Qin and Yang, 2019), may there is great progress in mitigating bias in text, be prone to bias given the underrepresentation of understanding its presence in multimodal speech several demographics across race, gender, native based analysis, in real world scenarlanguage, etc. in the financial realm
In Proceedings of The Web Conference 2020, pages 441–451
Summary
Bias in Finance Public financial data is impacting virtually every aspect of investment decision making (Pericet al., 2016; Brynjolfsson et al, 2011). Neural models on multimodal financial data to forecast volatility (Cornett and Saunders, 2003; Trippi trinsic to different genders can inculcate semantic and Turban, 1992) and minimize risk. These mod- gender bias (Li et al, 2019; Suresh and Guttag, els effective, may be tainted by bias due 2019). Building upon the work of Qin and ies show that models trained on gender imbalanced Yang (2019); Yang et al (2020) our main focus data reduce the chances for women to get capi- is to learn a function f (E{T,A}) → v[0,τ], over tal investments or loans (Gürdeniz et al, 2020). Apart from that, using feature representations in- different time periods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
