SoFiE Financial Econometrics Summer School
"Machine Learning in Finance"
August 2-August 6, 2021
Volatility Institute, NYU Shanghai
Note*: The application of this year Summer School has been closed, if you have questions or concerns, please reach out to the email@example.com supporting this event.
NOTE 1: Due to ongoing COVID Restrictions, the lectures and all other activities will take place over Zoom.
NOTE 2: Time to be confirmed according to different time zone.
The SoFiE Financial Econometrics Schools are annual week-long research-based courses for Ph.D. students and new faculty in financial econometrics. For the first two years, the Summer School was held at Oxford University’s Oxford-Man Institute and in 2014 it moved to Harvard University. In 2015 and 2016, it was held in Brussels. Since 2017, The SoFiE Financial Econometrics Summer School took place in North America, Asia and Europe. In 2018, 2019 and 2020, it was held at the Volatility Institute of NYU Shanghai.
The editorial board for these annual series is made up of professors as follows:
Torben G. Andersen (Northwestern University)
Francis X. Diebold (University of Pennsylvania, past President of SoFiE)
Eric Ghysels (University of North Carolina, Chapel Hill, Secretary and Founding Co-President of SoFiE)
Ravi Jagannathan (Northwestern and past President of SoFiE)
Per Mykland (University of Chicago and past President of SoFiE)
Eric Renault (Brown University and past President of SoFiE)
Neil Shephard (Harvard University)
Viktor Todorov (Northwestern University)
The course is intended for Ph.D. students and researchers in statistics, econometrics and finance. It covers an introduction to statistical machine learning methods such as LASSO, SCAD, kernel machine, support vector machines, tree-based methods, boosting, random forests, deep neural networks, topic modeling, and their applications in financial prediction, including cross-sectional asset pricing, high-frequency trading, forecasting equity and bond risk premia, sentiment analysis of financial news, and housing price prediction.
This course is open to all students and researchers who apply to attend and are admitted. The course will offer a limited number of course participants an opportunity to present their current research and receive feedback from the instructors and other course participants. Students interested in making a presentation (which is entirely optional) should indicate so on their application and submit the research paper that will form the basis of their presentation. Students who are selected to make a presentation will be informed at the same time as they receive their admission decisions.
Students will be provided with a packet of lecture notes when the course starts.
Professor Jianqing Fan (Princeton University)
Jianqing Fan is the Frederick L. Moore’1918 Professor of Finance, Professor of Operations Research and Financial Engineering, and former Chairman of Department of Operations Research and Financial Engineering at the Princeton University. He previously held professorships at CUHK, UNC-Chapel Hill, and UCLA. He has authored or co-authored over 200 articles on financial econometrics, statistical machine learning, analysis of Big Data, and various aspects of theoretical and methodological statistics and finance. His finance work focuses on the analysis of high-frequency finance, portfolio allocation, risk management, time series, high-dimensional data, statistical machine learning, and non-parametric modelling. His published work has been recognized by the 2000 COPSS Presidents’ Award, the 2007 Morningside Gold Medal of Applied Mathematics, Guggenheim Fellowship in 2009, Academician of Academia Sinica 2012, Guy Medal in Silver in 2014, and Noether Senior Award in 2018. He is an Elected Fellow of the American Association for Advancement of Science, the Institute of Mathematical Statistics, the American Statistical Association, and the Society of Financial Econometrics, and a past President of the Institute of Mathematical Statistics. He is the co-editor of Journal of Business and Economics Statistics and past co-editor of Journal of Econometrics, Annals of Statistics, Probability Theory and Related Fields, and Ecnometrics Journal, and has served as an associate editor of Journal of American Statistical Association, Econometrica, and Journal of Financial Econometrics.
Professor Dacheng Xiu (The University of Chicago Booth School of Business)
Dacheng Xiu is Professor of Econometrics and Statistics at the University of Chicago Booth School of Business. His research interests include developing statistical methodologies and applying them to financial data, while exploring their economic implications. His earlier research involved risk measurement and portfolio management with high-frequency data and econometric modeling of derivatives. His current work focuses on developing machine learning solutions to big-data problems in empirical asset pricing. Xiu’s work has appeared in Econometrica, Journal of Political Economy, Journal of Finance, Review of Financial Studies, Journal of the American Statistical Association, and Annals of Statistics. He is a Co-Editor for the Journal of Financial Econometrics, an Associate Editor for the Journal of Econometrics, Journal of Business & Economic Statistics, Management Science, Journal of Applied Econometrics, the Econometrics Journal, and Journal of Empirical Finance. He has received several recognitions for his research, including Fellow of the Society for Financial Econometrics, Fellow of the Journal of Econometrics, Swiss Finance Institute Outstanding Paper Award, AQR Insight Award, and Best Conference Paper Prize from the European Finance Association.
The syllabus of the course is as follows:
1. Building statistical machine learning models
1.1 Multiple regression
1.2 Model Building
1.3 Ridge Regression
1.4 Regression in RKHS
1.6 Generalized Linear Model
1.7 Housing price prediction
2. Modeling Selection and Feature Screening
2.1 Penalized Least-squares
2.2 Penalized Likelihood
2.3 Feature Screening
2.4 Asset Pricing with Text Data
3. Supervised Learning
3.1 Model-based Classifiers
3.2 Density classifier, Naïve Bayes, Features Augmentation
3.3 Nearest Neighbor Classifiers
3.4 Classification and Regression Trees and Ensemble methods
3.5 Support Vector Machines
3.6 High-frequency trading
4. Unsupervised Learning
4.1 k-mean and hierarchical clustering
4.2 Learning latent risk factors
4.3 Cross-sectional asset pricing
4.4 Test of alphas
4.5 Robust covariance inputs and factor adjustments
5. Deep Learning
5.2 FNN, CNN and RNN
5.3 Generative Adversary Networks
5.4 Training Algorithms
5.5 A Glimpse of Theory
5.6 Autoencoder Asset Pricing Models
5.7 Predicting Returns using OHLC Charts
The applications should include a full CV and motivation letter (half-page length) explaining why attending this course would be helpful to the applicant’s research work. All materials should be in pdf version. The application deadline is 15 May, 2021. Decisions will be emailed out by 1 June, 2021.
Applicants are encouraged to present some of their thesis work during evening sessions. For this, they should preferably append a paper to their application. They can submit an extensive abstract if the paper is not yet finished. The paper topics need not be closely linked to the course but obviously must be in the field of financial econometrics. Papers will be selected by the organizing committee on the basis of their quality.
$300 for Ph. D. students and faculty members attending this course.
$600 for Ph.D. level colleagues from other institutions.
Confirmed admission of a selected applicants will be conditional on the fee payment in due time (details will be provided in the admission email).
To receive an invoice, please fill the information in this link
All accepted participants will be expected to be members of the Society for Financial Econometrics or join before their place is confirmed.
See http://sofie.stern.nyu.edu/membership on how to join the society (where a student membership option is available).
* Use Worldclock to conveniently convert these China Standard Time (Shanghai City) to your time zone.