lecture: prediction of stock and bond markets based on big data and machine learning-凯发游戏

 lecture: prediction of stock and bond markets based on big data and machine learning-凯发游戏
english > events > content
lecture: prediction of stock and bond markets based on big data and machine learning

hits: date:2021-04-09 15:42

date: april 14, 2021

time: 15:00 pm

tencent conference no.:137 733 527

event details:

lecturer: professor jiang, fuwei

about the lecturer:

jiang, fuwei, phd in finance, dean, professor, ph.d. supervisor of financial engineering department of central university of finance and economics. his research areas include asset pricing, behavioral finance, financial technology, etc.. he has published more than 30 papers in the top financial journals such as journal of financial economics, review of financial studies, management science, "financial research", "journal of management science", "economic quarterly", etc., and presided over 5 projects of the national natural science foundation of china. he served as the communications review of national natural science foundation of china , the review expert of the ministry of education degree center, the editorial board of ssci source journal, and anonymous review of more than 30 chinese and english academic journals. his results were rated as the top 1% of the world’s highest cited papers and rfs highly cited papers in the esi economic management category. his papers were reprinted and applied by harvard business review, tsinghua financial review, duke university global financial market research center, china merchants securities, ubs, etc., and won the "financial research" excellent paper award, the asian finance association's the best paper award, the best paper award of the international financial management association and other academic awards.

about the lecture:

we provide a comprehensive study on the cross-sectional predictability of corporate bond returns using big data and machine learning. we examine whether a large set of equity and bond characteristics drive the expected returns on corporate bonds. using either set of characteristics, we find that machine learning methods substantially improve the out-of-sample predictive power for bond returns, compared to the traditional linear regression models. while equity characteristics produce significant explanatory power for bond returns, their incremental predictive power relative to bond characteristics is economically and statistically insignificant. bond characteristics provide as strong forecasting power for future equity returns as using equity characteristics alone. however, bond characteristics do not offer additional predictive power above and beyond equity characteristics when we combine both sets of predictors.