PKU

MAFS 5440. Artificial Intelligence in Fintech
Fall 2024


Course Information

Synopsis

This course offers a comprehensive exploration of the fundamental concepts and underlying principles of artificial intelligence (AI). It delves into the core principles of machine learning and provides valuable insights through case studies of relevant technologies. By providing opportunities for hands-on experimentation with machine learning applications, the course aims to inspire students to devise innovative approaches to address real-life problems in fintech using readily-available AI technologies.
Prerequisite: Some preliminary course on (statistical) machine learning, applied statistics, and deep learning will be helpful.

Instructors:

Yuan Yao

Time and Place:

Wednesday 19:30-22:20pm, Lecture Theatre G (LTG)

Reference (参考教材)

An Introduction to Statistical Learning, with applications in R / 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. CAO, He and Ms. LIU, Xuantong < aifin.hkust (add "AT gmail DOT com" afterwards) >

Schedule

Date Topic Instructor Scriber
04/09/2024, Wed Lecture 01: Overview and History of Artificial Intelligence in Fintech. [ slides A ][ slides B ]
    [ Project 1 ]
  • Warm-up project description [ pdf ]
  • Kaggle: Home Credit Default Risk [ link ]
Y.Y.
11/09/2024, Wed Lecture 02: Supervised Learning: Linear Regression and Classification [ slides ] Y.Y.
25/09/2024, Wed Lecture 03: Model Assessment and Selection: Subset, Ridge, Lasso, and PCR [ slides ]
Y.Y.
29/09/2024, Sun Lecture 04: Decision Tree, Bagging, Random Forests and Boosting [ slides ]
Y.Y.
02/10/2024, Wed Lecture 05: Support Vector Machines [ slides ]
Y.Y.
06/10/2024, Sun Lecture 06: An Introduction to Convolutional Neural Networks [ slides ]
Y.Y.
09/10/2024, Wed Lecture 07: Other nonlinear models moving beyond linearity [ slides ]
    [ Project 2 ]
  • Project description: paper replication study [ pdf ]
  • Asset Pricing paper replication [ pdf ]
  • Reimaging paper replication [ pdf ]

  • 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 ]

Y.Y.
16/10/2023, Wed Lecture 08: An Introduction to Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM) [ slides ]
Y.Y.
23/10/2024, Wed Lecture 09: Attention and Transformers [ slides ]
    [ Guest Talk ]
  • Title: Sharing from Super Quantum Fund
  • Speaker: Invited guests from Super Quantum
  • Introduction: Super Quantum is a quantitative asset management firm founded in 2019 by Professor Michael Zhang. With a vision to bring ‘genuine’ science to investing in the opportunistic China-A share market, the team combines state-of-the-art research on deep learning, mathematics, econometrics and statistics, with solid experience in the finance industry to design quantitative strategies that consistently outperform the market. Super Quantum currently manages 5-10 billion RMB and has Type 9 (asset management) license from SFC in Hong Kong.
Y.Y.
30/10/2024, Wed Lecture 10: Transformer and Applications [ slides ]
Y.Y.
06/11/2024, Wed Lecture 11: 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 ]
  • Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution, by Zijie Zhao, Roy E. Welsch. [ arXiv:2410.14927 ]
  • Prof. Michael Kearns, University of Pennsyvania, Algorithmic Trading and Machine Learning, Simons Institute at Berkeley [ link ]
Y.Y.
13/11/2024, Wed Lecture 12: Final Project.
    [ Reference ]
  • Kaggle: Jane Street 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 ]
    [ Reference: Guest Talk ]
  • Title: Sequential Predictive Conformal Inference for Time Series [ slides ]
  • Speaker: Chen XU, Georgia Institute of Technology
  • Abstract: We present a new distribution-free conformal prediction algorithm for sequential data (e.g., time series), called the sequential predictive conformal inference (SPCI). We specifically account for the nature that time series data are non-exchangeable, and thus many existing conformal prediction algorithms are not applicable. The main idea is to adaptively re-estimate the conditional quantile of non-conformity scores (e.g., prediction residuals), upon exploiting the temporal dependence among them. More precisely, we cast the problem of conformal prediction interval as predicting the quantile of a future residual, given a user-specified point prediction algorithm. Theoretically, we establish asymptotic valid conditional coverage upon extending consistency analyses in quantile regression. Using simulation and real-data experiments, we demonstrate a significant reduction in interval width of SPCI compared to other existing methods under the desired empirical coverage. Source codes can be found at [ GitHub ].
  • Bio: Chen Xu is currently a 4th year Operations Research PhD at Georgia Tech ISyE, where he is supervised by Prof. Yao Xie. His current research interests are two-fold. (1) Uncertainty quantification for machine learning models. Specifically, advance conformal prediction as a distribution-free method for arbitrarily complex deep models, especially in the context of time-series modeling. (2) Generative models through flow-based neural networks. Specifically, develop scalable computational tools for problems at the intersection of statistics and optimization, including extensions to high-dimensional optimal transport, distributionally robust optimization, and differential privacy. He has published in top machine learning conferences (e.g., ICML 2021 oral, NeurIPS 2023 spotlight) and journals (e.g., IEEE TPAMI 2023, IEEE JSAIT).
Y.Y.

by YAO, Yuan.