A Semiparametric Gaussian Copula Regression Model for Predicting Financial Risks from Earnings Calls

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1155–1165, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics A Semiparametric Gaussian Copula Regression Model for Predicting Financial Risks from Earnings Calls William Yang Wang School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 yww@cs.cmu.edu Zhenhao Hua School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 zhua@cs.cmu.edu Abstract Earnings call summarizes the financial performance of a company, and it is an important indicator of the future financial risks of the company. We quantitatively study how earnings calls are correlated with the financial risks, with a special fo- cus on the financial crisis of 2009. In par- ticular, we perform a text regression task: given the transcript of an earnings call, we predict the volatility of stock prices from the week after the call is made. We pro- pose the use of copula: a powerful statis- tical framework that separately models the uniform marginals and their complex mul- tivariate stochastic dependencies, while not requiring any prior assumptions on the distributions of the covariate and the de- pendent variable. By performing probabil- ity integral transform, our approach moves beyond the standard count-based bag-of- words models in NLP, and improves pre- vious work on text regression by incor- porating the correlation among local fea- tures in the form of semiparametric Gaus- sian copula. In experiments, we show that our model significantly outperforms strong linear and non-linear discriminative baselines on three datasets under various settings. 1 Introduction Predicting the risks of publicly listed companies is of great interests not only to the traders and ana- lysts on the Wall Street, but also virtually anyone who has investments in the market (Kogan et al., 2009). Traditionally, analysts focus on quantita- tive modeling of historical trading data. Today, even though earnings calls transcripts are abun- dantly available, their distinctive communicative practices (Camiciottoli, 2010), and correlations with the financial risks, in particular, future stock performances (Price et al., 2012), are not well studied in the past. Earnings calls are conference calls where a listed company discusses the financial perfor- mance. Typically, a earnings call contains two parts: the senior executives first report the oper- ational outcomes, as well as the current financial performance, and then discuss their perspectives on the future of the company. The second part of the teleconference includes a question answering session where the floor will be open to investors, analysts, and other parties for inquiries. The ques- tion we ask is that, even though each earnings call has distinct styles, as well as different speakers and mixed formats, can we use earnings calls to predict the financial risks of the company in the limited future? Given a piece of earnings call transcript, we investigate a semiparametric approach for auto- matic prediction of future financial risk1. To do this, we formulate the problem as a text regres- sion task, and use a Gaussian copula with prob- ability integral transform to model the uniform marginals and their …

Content truncated to 500 words