MH6805 · Postgraduate

Machine Learning in Finance

MSc in Financial Technology

Course materials and assessment information for registered students are provided through NTULearn. External resource links may require NTU access.

Overview

In order to appreciate the future changes on the finance industry that will be caused by machine learning, it is necessary to understand the key components of machine learning in finance.

Learning Objectives and Outcomes

This course covers essential machine learning techniques in finance. The emphasis is placed on the financial applications and how can they transform the finance industry. This course will cover supervised learning, unsupervised learning, and deep learning. This course will also train the students’ soft skills through the group project on realistic data analysis problem.

Assessment Scheme

[10%] Class Participation
[20%] Assignments _ Week 5 (Unsupervised Learning), Week 8 (Supervised Learning), Week 14 (Deep Learning)
[35%] Quiz _ Week 9 (Unsupervised and Supervised Learning)
[35%] Group Project (Presentation & Report) _ Week 13

Topics

[4hrs] Introduction of Machine Learning and Types of Data and Errors: Data Pre-processing and Bias-Variance Trade-off
[3hrs] Unsupervised Learning I: Clustering and Dimension Reduction [Lab]
[3hrs] Supervised Learning I: KNN and Resampling [Lab]
[4hrs] Supervised Learning II: Regression and Regularization [Lab]
[3hrs] Supervised Learning III: Logistic Regression [Lab]
[4hrs] Supervised Learning IV: Decision Trees and Ensemble Methods [Lab]
[3hrs] Supervised Learning V: Support Vector Machines [Lab]
[4hrs] Deep Learning I: Feedforward Neural Networks [Lab]
[3hrs] Deep Learning II: Convolutional Neural Networks [Lab]
[3hrs] Deep Learning III: Long Short-Term Memory [Lab]
[3hrs] Unsupervised Learning II: Hidden Markov Model and Kalman Filter

References

[Textbook] G. James, D. Witten, T. Hastie, and R. Tibshirani. (2021) An Introduction to Statistical Learning - with Applications in R (2nd Ed.). Springer.

[Textbook] J. C. Hull. (2021) Machine Learning in Business: An Introduction to the World of Data Science (3rd Ed.). Independently Published.
T. Hastie, R. Tibshirani, and J. Friedman. (2009) The Elements of Statistical Learning - Data Mining, Inference, and Prediction (2nd Ed.). Springer.
B. Ripley. (1996) Pattern Recognition and Neural Networks. Cambridge University Press.
I. Goodfellow, Y. Bengio, and A. Courville. (2016) Deep Learning. MIT Press.
M. L. de Prado. (2018) Advances in Financial Machine Learning. Wiley.

Remark: The first and third books (about statistical learning) can be downloaded for free from their websites. The fifth book (about deep learning) is viewable online.

Useful Links about Data Analysis Techniques

Data Mining Map (Credits: S. Sayad): Clicking the buttons of topics directs to the topics' introduction pages.
Collection of Data Analysis Techniques (Credits: DSS at Princeton): Most of them are illustrated with the R/Stata examples.
R & Data Mining (Credits: RDataMining.com): Presents documents, examples, tutorials, and resources on R and data mining.

Useful Links for Projects

Advice for Applying Machine Learning (Credits: Andrew Ng): Very good advice on how to diagnose an algorithm and start a learning problem.
Kaggle (Credits: Kaggle.com): Contains a collection of datasets for data analysis and machine learning
UCI Machine Learning Repository (Credits: UC Irvine): Contains a number of data sets with clear descriptions and objectives.
Some Suggestions for Term Papers and Projects (Credits: P.-N. Tan, M. Steinbach, and V. Kumar): Some research papers on different project topics.