讲座时间：5月9日9:00-11:30

讲座地点：管楼G506

讲座主题：Machine Forecast Disagreement in the Cryptocurrency Market

讲座嘉宾简介

沈德华，南开大学金融学院教授、博士生导师、百名青年学科带头人、爱思唯尔中国高被引学者（2022-2024年、入选学科领域：应用经济学）。现任中国管理现代化研究会金融管理专业委员会副秘书长、中国优选法统筹法与经济数学研究会青年工作委员会副秘书长、中国工业与应用数学学会区块链专业委员会委员和中国信息经济学会理事等职务。主持国家自然科学基金青年科学基金1项、面上项目2项、天津市青年人才托举工程1项以及作为青年骨干参与国家自然科学基金重大项目1项。研究成果获首届系统科学与系统工程优秀博士学位论文奖、欧洲金融管理协会读者评选最佳论文奖、第十八届中国管理学年会优秀论文以及第八届高等学校科学研究优秀成果奖二等奖等。

讲座摘要

This paper uses machine learning models to construct a crypto-level measure of investor belief disagreement (MFD) for cryptocurrencies. Investors use their individual models and common data information to form their individual return forecasts. Consistent with Miller (1977), we find a significant and negative relation between belief disagreement and future returns in the cross section in the cryptocurrency market. The negative MFD-return relation holds in various robustness tests. In particular, MFD significantly predicts future returns after controlling for other disagreement proxies such as turnover. Moreover, the negative relation is stronger for cryptocurrencies with larger limits-to-arbitrage or more severe overpricing. The negative relation is stronger following high crypto investor sentiment periods. Our results suggest that the negative MFD-return relation is mainly driven by mispricing and limits-to-arbitrage.