PKU

MAFS 6010Z. Artificial Intelligence in Fintech
Fall 2021

Course Information

Synopsis

This course explores the basic concepts and underlying principles of artificial intelligence (AI), delving into the fundamentals of machine learning with insights from case studies of relevant technologies. Allowing for the experimentation of applications of machine learning, this course is designed to encourage students to devise creative ways to put readily-available AI technologies to use to tackle problems in real life. With a focus on the conceptual understanding of the fundamentals of AI, the purpose of this course is two-fold:


Prerequisite: Some preliminary course on (statistical) machine learning, applied statistics, and deep learning will be helpful.

Instructors:

Yuan Yao

Time and Place:

Thursday 7:30-10:20pm, Lecture Theater G and Zoom from CANVAS, HKUST

Reference (参考教材)

An Introduction to Statistical Learning, with applications in R or Python. By James, Witten, Hastie, and Tibshirani

ISLR-python, By Jordi Warmenhoven.

ISLR-Python: Labs and Applied, by Matt Caudill.

Manning: Deep Learning with Python, by Francois Chollet [GitHub source in Python 3.6 and Keras 2.0.8]

MIT: Deep Learning, by Ian Goodfellow, Yoshua Bengio, and Aaron Courville

Tutorials: preparation for beginners

Python-Numpy Tutorials by Justin Johnson

scikit-learn Tutorials: An Introduction of Machine Learning in Python

Jupyter Notebook Tutorials

PyTorch Tutorials

Deep Learning: Do-it-yourself with PyTorch, A course at ENS

Tensorflow Tutorials

MXNet Tutorials

Theano Tutorials

The Elements of Statistical Learning (ESL). 2nd Ed. By Hastie, Tibshirani, and Friedman

statlearning-notebooks, by Sujit Pal, Python implementations of the R labs for the StatLearning: Statistical Learning online course from Stanford taught by Profs Trevor Hastie and Rob Tibshirani.

Teaching Assistant:


Email: Mr. WANG, He < aifin.hkust (add "AT gmail DOT com" afterwards) >

Schedule

Date Topic Instructor Scriber
02/09/2021, Thu Lecture 01: Overview and History of Artificial Intelligence in Fintech. [ slides ]
    [ Guest Talk ]
  • Title: An Overview of Quant Modeling and Trading: Theory and Practice [ slides ]
  • Speaker: Prof. Michael Zhang, CUHK
  • Bio: Professor Michael Zhang is a Chair Professor of Decision Sciences and Managerial Economics at the Chinese University of Hong Kong. He serves as the Associate Dean of Innovation and Impact, Co-Executive Director of Asia Pacific Institute of Business, Co-Director of Hong Kong-Shenzhen Finance Research Centre at the CUHK Business School. Externally, he is also affiliated with MIT Initiative on Digital Economy, Guanghua School of Management of Peking University and Leibniz Centre for European Economic Research (ZEW). He has a PhD in Management from MIT Sloan School of Management, an MSc in Management, a BE in Computer Science and a BA in English from Tsinghua University. Before joining the academia, he worked as an analyst for an investment bank, and as an international marketing manager for a high-tech company. He holds a US patent, and cofounded several companies in Social Networking (Unknown Space, MITBBS, the biggest social network for Chinese in America) and FinTech (Super Quantum Fund).
Y.Y.
09/09/2021, Thu Lecture 02: Supervised Learning: Linear Regression and Classification [ slides ] Y.Y.
16/09/2021, Thu Lecture 03: Model Assessment and Selection: Subset, Ridge, Lasso, and PCR [ slides ]
Y.Y.
23/09/2021, Thu Lecture 04: Decision Tree, Bagging, Random Forests and Boosting [ YY's slides ]
Y.Y.
30/09/2021, Thu Lecture 05: Support Vector Machines [ YY's slides ]
Y.Y.
07/10/2021, Thu Lecture 06: An Introduction to Convolutional Neural Networks [ YY's slides ]
    [Reading Material]:
  • Shihao Gu, Bryan Kelly and Dacheng Xiu
    "Empirical Asset Pricing via Machine Learning", Review of Financial Studies, Vol. 33, Issue 5, (2020), 2223-2273. Winner of the 2018 Swiss Finance Institute Outstanding Paper Award.
    [ link ]

  • Jingwen Jiang, Bryan Kelly and Dacheng Xiu
    "(Re-)Imag(in)ing Price Trends", Chicago Booth Report, Aug 2021
    [ link ]

  • Tracy Ke, Bryan Kelly and Dacheng Xiu
    "Predicting Returns with Text Data", Aug. 2021. Winner of the 2019 CICF Best Paper Award.
    [ link ]

Y.Y.
21/10/2021, Thu Lecture 07: Introduction of quantitative investing with machine learning
    [ Guest Talk ]
  • Title: Introduction of quantitative investing with machine learning [ slides ]
  • Speaker: Prof. Haifeng You, HKUST
  • Bio: Haifeng You is a Professor of Accounting and Co-Director of the Center for Securities Analysis with Financial Technology at Hong Kong University of Science and Technology (HKUST). His research focuses on the role of financial information and financial technology in equity investment. He has published on leading academic and professional journals such as Journal of Financial Economics, Journal of Accounting and Economics, and Financial Analyst Journal. Previously, he served as the Head of Quantitative Equity Research at China Investment Corporation and Quantitative Researcher at Barclays Global Investors. He has also served as advisors and consultants for investment firms such as GSA capital in the UK and China Pacific Asset Managemen and Bosera Asset Management in China, helping them to build Asian and global quantitative equity strategies. Professor You holds a PhD degree in Accounting from University of California, Berkeley and a BA degree in Finance from Peking University.
Haifeng You
Y.Y.
28/10/2021, Thu Lecture 08: An Introduction to Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM) [ YY's slides ]
Y.Y.
04/11/2021, Thu Lecture 09: Attention, Transformer and BERT [ YY's slides ]
    [ Guest Talk ]
  • Title: Network Design and Some Thoughts About Trading by DNN [ slides ]
  • Speaker: Dr. Yijie Lu, AQUMON
  • Abstract: This talk presents the evolution of deep neural network design from the perspective of solving image classification problems. We explain why deep models are superior than classic machine learning models and how to take advantage of it. We also introduce deep learning applications by a variety of networks. In terms of trading, we will discuss both potentials and challenges of deep models, and how AQUMON embraces innovation and help achieve the goal.
  • Bio: Yijie Lu received his Ph.D. in Computer Science from City University of Hong Kong in 2018. He was an active participant in NIST TRECVID and the best performer on both Zero-Example Multimedia Event Detection and Multimedia Event Recounting. Participants of this annual workshop included 30 renowned research institutes and companies worldwide. In 2013, he interned in Multimedia Search and Mining Group at Microsoft Research Asia, Beijing. Prior to that, he received the B.Eng. and M.S. degrees in Computer Science at Southwest Jiaotong University, Chengdu.
Y.Y.
11/11/2021, Thu Lecture 10: An Introduction to Reinforcement Learning with Applications in Quantitative Finance [ slides ]
    [ Reference ]:
  • Google DeepMind's Deep Q-learning playing Atari Breakout: [ youtube ]
  • To view .ipynb files below, you may try [ Jupyter NBViewer]
  • Deep Q-Learning Pytorch Tutorial: [ link ]
  • A Tutorial of Reinforcement Learning for Quantitative Trading: [ Tutorial ] [ Replicate ]
  • FinRL: Deep Reinforcement Learning for Quantitative Finance [ GitHub ]
  • Reinforcement Learning and Supervised Learning for Quantitative Finance: [ link ]
  • Prof. Michael Kearns, University of Pennsyvania, Algorithmic Trading and Machine Learning, Simons Institute at Berkeley [ link ]
Y.Y.
18/11/2021, Thu Lecture 11: Topics on Blockchains and Final Project.
    [ Guest Talk ]
  • Title: Cefi or Defi [ slides ]
  • Speaker: Dr. Alex Yang, Founder & CEO, Volmart Inc.
  • Abstract: starting from the evolution of traditional financial derivatives to blockchain smart contract enabled new transactions, with samples in AMM, yield enhancement and derivatives.
  • Bio: Alex Yang is CEO of Volmart, a volatility marketplace for digital assets. Powered by its proprietary volatility risk engine and defi smart contracts, Volmart is the world’s first hybrid risk manager offering digital asset structured products, aiming to build one stop shop for customized digital asset service. Our mission is to pave the road connecting Crypto Street and Wall Street. Prior to Volmart, he was CEO of V Systems, a blockchain project led by Sunny King, a legendary developer and creator of Proof-of-Stake consensus. As CEO of VSYS, Alex was driving the project to solve the core scalability and stability problems to apply blockchain technology to real industry. Prior to moving into blockchain industry, Alex was head of APAC structured rates trading at Nomura International, and head of China Structured Products at FICC, UBS HK. He started his career as a quantitative developer at Jump Trading in Chicago.
    Alex has a PhD from Northwestern University and a BA in Mathematics from Peking University.
    [ Reference ]:
  • Kaggle: G-Research Crypto Forecasting. [ link ]
  • Kaggle: M5 Forecasting - Accuracy, Estimate the unit sales of Walmart retail goods. [ link ]
  • Kaggle: M5 Forecasting - Uncertainty, Estimate the uncertainty distribution of Walmart unit sales. [ link ]
  • Kaggle: Home Credit Default Risk [ link ]
  • Kaggle: COVID-19 Open Research Dataset Challenge (CORD-19) [ link ]
Alex Yang
Y.Y.
25/11/2021, Thu Lecture 12: An Introduction to Unsupervised Learning: PCA, AutoEncoder, VAE, and GANs [ slides ]
Y.Y.
by YAO, Yuan.