Time: 4:30pm – 5:30pm, Thursday, May 2

Venue: IB 1050

Speaker: Halis Sak, Assistant Professor at Shenzhen Audencia Financial Technology Institute (SAFTI), WeBank Institute of Fintech, Shenzhen University

Host: Gergely Horvath, Associate Professor of Economics, Duke Kunshan University

Speaker’s bio: Halis Sak is an Assistant Professor at Shenzhen Audencia Financial Technology Institute (SAFTI), WeBank Institute of Fintech, Shenzhen University. Before joining the institute, he was a Visiting Assistant Professor at the Department of Finance of HKUST. His research and teaching address machine learning, empirical asset pricing, risk management, and Monte Carlo simulation. His academic works appeared in journals such as Review of Finance, Quantitative Finance, and European Journal of Operational Research.

Abstract: By identifying links between stocks through the similarity of news content, we find that the past performance of interconnected peer stocks can be utilized for predicting stock returns. The corresponding long-short portfolio generates a monthly return of 0.74%. The return predictability remains after adjusting factor risks and controlling related firm characteristics. Further evidence shows that firms with similar news content have close fundamental connections; their financial performance is linked with each other and their analysts update forecasts concurrently. Our paper highlights the role of news similarity as a measure of firm linkage and provides a new aspect on momentum spillover effects.