科学研究

韩冰，加拿大多伦多大学罗特曼管理学院金融学教授，多伦多证券交易所资本市场讲座教授。韩冰教授的主要研究领域是资产定价、投资、行为金融学、房地产金融。他的多篇论文发表在顶级经济、金融和管理学学术杂志上，包括Journal of Finance、Journal of Financial Economics、Review of Financial Studies、Review of Economic Studies、International Economic Review、Journal of Economic Theory、Management Science等。研究成果受到《纽约时报》《华尔街日报》《华盛顿邮报》《经济学人》等媒体的专访和报导。获得众多国际知名学术奖项，包括欧洲金融协会最佳论文奖、中国金融协会会议最佳论文奖、美国个人投资者协会在资产定价研究中获优秀论文奖、上海风险论坛最佳论文奖、中国国际金融与政策论坛杰出论文奖、全球金融专业人士协会终身成就奖。韩冰教授现任Financial Management、Journal of Economic Dynamics and Control、Journal of Empirical Finance、International Review of Finance和Pacific-Basin Finance Journal主编和副主编。

This paper investigates whether text data contains useful information about the cross-section of expected equity option returns. We apply both lexicon-based and machine learning approaches to extract qualitative signals from over six million news articles. The machine learning methods outperform lexicon-based approaches in predicting delta-hedged option returns and generate sizable profits. Our results are robust after controlling for known option return predictors including volatility-related variables and various underlying stock characteristics. An analysis of the keywords identified by machine learning methods suggests the option return predictability is largely related to firm-specific sentiment and option mispricing. Our work highlights the importance of analyzing unstructured data like texts for pricing derivatives.