Forecasting Financial Market Volatility Using a Dynamic Topic Model

作     者：Morimoto, Takayuki Kawasaki, Yoshinori 

作者机构：Kwansei Gakuin Univ Dept Math Sci 2-1 Gakuen Sanda Hyogo 6691337 Japan Inst Stat Math Dept Stat Modeling 10-3 Midori Cho Tachikawa Tokyo 1908562 Japan SOKENDAI 10-3 Midori Cho Tachikawa Tokyo 1908562 Japan 

出 版 物：《ASIA-PACIFIC FINANCIAL MARKETS》 (亚洲太平洋金融市场)

年 卷 期：2017年第24卷第3期

页      面：149-167页

学科分类：0202[经济学-应用经济学] 02[经济学] 0201[经济学-理论经济学] 

基　　金：Grants-in-Aid for Scientific ResearchMinistry of Education  Culture  Sports  Science and Technology  Japan (MEXT)Japan Society for the Promotion of ScienceGrants-in-Aid for Scientific Research (KAKENHI) [16K00067  15K03406] Funding Source: KAKEN 

主　　题：Big data Online news Dynamic topic model Topic score Forecasting Realized volatility 

摘      要：This study employs big data and text data mining techniques to forecast financial market volatility. We incorporate financial information from online news sources into time series volatility models. We categorize a topic for each news article using time stamps and analyze the chronological evolution of the topic in the set of articles using a dynamic topic model. After calculating a topic score, we develop time series models that incorporate the score to estimate and forecast realized volatility. The results of our empirical analysis suggest that the proposed models can contribute to improving forecasting accuracy.