[Celebration Lecture] Jianqing Fan：How much can machine learn finance?
Time: 9:00-10:00am, Oct. 6th, 2021, Wednesday
Venue: ZOOM（ID：81302052167；password：388334）
Spreker: Jianqing Fan, Professor, Princeton University
Abstract:This talk focuses on how to use statistical machine learning techniques and big data to solve problems in finance and economics. It begins with an overview on the genesis of machine learning and AI and how statistical and computational methods have evolved with growing dimensionality and sample sizes and become the foundation of modern machine learning and AI. It introduces simple yet power techniques to deal with heavy tailness and dependence that stylize financial data. We showcase the applications in high frequency trading and sentiment learning from Chinese financial textual data.
We present the predictability in ultra high-frequency finance, with focus on the momentum measured by returns, trade directions, and duration that reflects trading speeds in very short time windows. Using statistical machine learning methods on complete transaction and quote update data of 101 stocks in the S\&P 100 index over two full years from 2019 to 2020, we quantified and documented the predictability and confirmed that it exists universally. For a median stock, a 10.5% out-of-sample R-square of 5-second trade returns can be predicted using merely past trade and quote data with about 64% of correctly predicting trade directions. The important predictors are unveiled. We also investigated how the predictability depends on the market environments and stock characteristics and the timeliness of data.
On the Chinese text analysis, we present a new framework for learning text data based on the factor model and sparsity regularization, called FarmPredict, to let machines learn financial returns directly. We validate our method using the literature on the Chinese stock market with several existing approaches. Based on approximately 2 million pieces of news from 2000 to 2019 downloaded from Sina Finance, we show that positive sentiments scored by our FarmPredict approach generate on average 83 bps daily excess returns, while negative news has.
Speaker’s Bio:Jianqing Fan（范剑青），美国普林斯顿大学终身教授，Frederick L. Moore'18冠名金融讲座教授，运筹与金融工程系教授和前任系主任，国际数理统计学会前主席，《Journal of Business and Economics Statistics》的主编。2000年荣获国际统计学领域最高奖项COPSS总统奖，2006年荣获洪堡基金会终身成就奖，2007年荣获晨兴华人数学家大会应用数学金奖，2013年获泛华统计学会（International Chinese Association）“许宝禄奖”，2014年荣获英国皇家统计学会授予的“Guy Medal”银质奖章，2018年荣获诺特资深学者奖（Noether Senior Scholar Award），此外，他还是国际统计学会（ISI）、国际数理统计学会（IMS）、美国科学促进会（AAAS）、美国统计学会（ASA）、计量金融学会（SOFIE）的会士，以及国际顶尖统计期刊《Annals of Statistics》、《Probability Theory and Related Field》及《Journal of Econometrics》等的前主编等。他的主要研究领域包括高维统计、机器学习、计量金融、时间序列、非参数建模，并在这些领域著有4本专著。
