Data mining is the automatic discovery of statistically interesting and potentially useful patterns from large amounts of data.  The goal of the course is to study the main methods used today for data mining and on-line analytical processing.  Topics include data mining architecture; data preprocessing; mining association rules; classification; clustering; on-line analytical processing (OLAP); data mining systems and languages; advanced data mining (web, spatial, and temporal data).

Assessment: 50% coursework and 50% examination

# This course offers an overview of current cloud technologies, and discusses various issues in the design and implementation of cloud systems. Topics include cluster systems architecture and example distributed/parallel programming paradigms; cloud delivery models (SaaS, PaaS, IaaS, and Serverless Computing) with examples from popular public cloud platforms; virtualization techniques such as hypervisor, virtual machines, and Docker; container orchestration and management tools, such as Kubernetes; distributed programming models and systems such as MapReduce and Apache Spark; and distributed file systems, such as Hadoop file system. Students will gain experience in setting up a containerised environment using Kubernetes for running distributed applications (e.g., Web applications, Spark applications) on public cloud environments (e.g., Amazon, Microsoft, Google, Alibaba).

Prerequisites: Students are expected to perform installation and administration of various open-source cloud/distributed software on their machines and the cloud. Basic understanding of Linux OS and administration, networking concepts and setup, and programming experiences (C/C++, Java, or Python) in a Linux environment are required.

Assessment: 50% coursework and 50% examination

# Pending University's approval

This course will teach a broad set of principles and tools that will provide the mathematical, algorithmic and philosophical framework for tackling problems using artificial intelligence (AI) and machine learning (ML).  AI and ML are highly interdisciplinary fields with impact in different applications, such as, biology, robotics, language, economics, and computer science.  AI is the science and engineering of making intelligent machines, especially intelligent computer programs, while ML refers to the changes in systems that perform tasks associated with AI.  Ethical issues in advanced AI and how to prevent learning algorithms from acquiring morally undesirable biases will be covered.

Topics may include a subset of the following: problem solving by search, heuristic (informed) search, constraint satisfaction, games, knowledge-based agents, supervised learning (e.g., regression and support vector machine), unsupervised learning (e.g., clustering), dimension reduction learning theory, reinforcement learning, transfer learning, and adaptive control and ethical challenges of AI and ML.

Pre-requisites:  Nil, but knowledge of data structures and algorithms, probability, linear algebra, and programming would be an advantage.

Assessment: 50% coursework and 50% examination

The course introduces our students to the field of Machine Learning, and help them develop skills of applying Machine Learning, or more precisely, applying supervised learning, unsupervised learning and reinforcement learning to solve problems in Trading and Finance.  This course will cover the following topics. (1) Overview of Machine Learning and Artificial Intelligence, (2) Supervised Learning, Unsupervised Learning and Reinforcement Learning, (3) Major algorithms for Supervised Learning and Unsupervised Learning with applications to Trading and Finance, (4) Basic algorithms for Reinforcement Learning with applications to optimal trading, asset management, and portfolio optimization, (5) Advanced methods of Reinforcement Learning with applications to high-frequency trading, cryptocurrency trading and peer-to-peer lending. 

Assessment: 65% coursework and 35% examination

Machine learning is a fast growing field in computer science and deep learning is the cutting edge technology that enables machines to learn from large-scale and complex datasets.  Ethical implications of deep learning and its applications will be covered first and the course will focus on how deep neural networks are applied to solve a wide range of problems in areas such as natural language processing, and image processing.  Other applications such as financial predictions, game playing and robotics may also be covered.  Topics covered include linear and logistic regression, artificial neural networks and how to train them, recurrent neural networks, convolutional neural networks, generative models, deep reinforcement learning, and unsupervised feature learning.

Prerequisites: Basic programming skills, e.g., Python is required.

Assessment: 40% coursework and 60% examination

This course provides students with the fundamentals of financial services in the context of e-Commerce and mobile devices.  Payment systems in general and various payment transaction systems in particular will be examined.  Similarly, eFinance has brought new concepts into e-Brokerage, e-Insurance, e-Lending and other fields.  The course covers technology, operations, customer experience as well as demonstrates how regulations and security aspects are impacted by developments like Bitcoin and Blockchain.  Studies of established banks as well as new FinTech Players serve as examples and reinforcements for many of the concepts.

Assessment: 40% coursework and 60% examination

This course provides the necessary fundamental concepts, theory and tools in Machine Learning (ML) to enable students to understand how Artificial Intelligence (AI) and ML can be applied in typical business applications in general, and for E-Commerce in particular.  As AI is a broad field of study, the course will focus on ML including an introduction to the fundamentals of ML, supervised and unsupervised learning, ML workflow, dataset preparation, handling and analysis, selection and training of ML models: regression, classification and clustering models; Support Victor Machines (SVM), decision trees, ensemble learning and random forests; introduction to Artificial Neural Networks (ANN) and other neural network models. The course will use ML projects and applications to demonstrate how ML can be used to solve real business problems.

Assessment: 100% coursework

This course introduces the major computation problems in the field of financial derivatives and various computational methods/techniques for solving these problems.  The lectures start with a short introduction on various financial derivative products, and then move to the derivation of the mathematical models employed in the valuation of these products, and finally come to the solving techniques for the models.

Pre-requisites:  No prior finance knowledge is required. Students are assumed to have basic competence in calculus and probability (up to the level of knowing the concepts of random variables, normal distributions, etc.).  Knowledge in at least one programming language is required for the assignments/final project.

Assessment: 40% coursework and 60% examination

This course introduces the tools and technologies widely used in industry for building applications for Quantitative Finance.  From analysis and design to development and implementation, this course covers: modelling financial data and designing financial application using UML, a de facto industry standard for object oriented design and development; applying design patterns in financial application; basic skills on translating financial mathematics into spreadsheets using Microsoft Excel and VBA; developing Excel C++ add-ins for financial computation.

Pre-requisites:  This course assumes basic understanding of financial concepts covered in COMP7802.  Experience in C++/C programming is required.

Assessment: 50% coursework and 50% examination

Selected topics in financial technology that are of current interest will be discussed.

Assessment: 50% coursework and 50% examination

Basics of financial markets; cash flow analysis; capital asset pricing model (CAPM); portfolio optimisation; arbitrage and fundamental theorem of asset pricing; types of derivatives including forward, futures and options for various underlying assets; returns, value-at-risk (VaR), utility functions; pricing and hedging of derivative securities; numerical studies.

Assessment: 30% coursework and 70% examination

This course will explore privacy and data protection in an increasingly interconnected data economy.  The Personal Data (Privacy) Ordinance and the data protection principles in particular will be studied in depth, making reference to relevant court judgments and Administrative Appeal Board cases.  Privacy protection under other ordinances and common law principles (such as breach of confidence, misuse of private information, nuisance, trespass, copyright infringement and defamation) will also be covered.  Emphasis will be made to the balance between privacy on the one hand and other rights as well as public and social interests on the other. The challenges posed by technological innovations and applications such as the internet, social media, mobile applications, cloud computing and Big Data will be highlighted. Specific topics to be addressed will include: (a) the concept of privacy and the genesis and development of its political, philosophical and economic underpinnings; (b) global development and international cooperation;(c) privacy and media intrusion; (d) regulation of direct marketing; (e) Privacy Commissioner for Personal Data: powers, functions and enforcement.  The course will focus on the Hong Kong situation but reference will be made to relevant international human rights instruments and the global and regional trends and developments.

Assessment: 40% research assignment and 60% take home examination

The overall aim of this is to help students understand how regulatory compliance and enforcement processes are being transformed by increased global competition and accelerating technological innovation in financial markets.

Topics covered will include how the role of information technology in the delivery of modern financial services has evolved over time as well as how recent developments in information technology are transforming compliance processes inside firms and enforcement efforts of regulators.

The impact of digital transformation of compliance in financial services on law firms, legal departments in companies, government attorneys, compliance managers, internal and external auditors, and system administrators will be considered.

A case study examining the impact of global competition and technology innovation on data protection/information privacy compliance efforts under Hong Kong, European Union and US law will be used to integrate theoretical and practical perspectives on the delivery of e-finance services.

Assessment: 10% class participation, 40% coursework and 50% take home examination

Money laundering and terrorist financing are examples of financial crimes that can, among other things, undermine the integrity and stability of financial institutions and the economic system at large, deter foreign investment, and distort international capital flows.  Money launderers and terrorist financiers are now deploying increasingly sophisticated methods and schemes to disguise and achieve their illicit purposes, and are particularly attracted to exploit those jurisdictions with weak or ineffective anti-money laundering (“AML”) and counter-terrorist financing (“CTF”) controls.  Thus, developing a solid and comprehensive understanding of the concepts of money laundering and terrorist financing as well as keeping abreast of the respective regulatory frameworks are crucial to appreciating and managing such risks and challenges in the context of a financial services business.

This course is designed to not only provide students with an overview of the legal and regulatory aspects of AML and CTF, but also to equip students with practical skills and best practices to detecting and managing these types of financial crime risks in a financial institution setting.  To achieve these objectives, this course is made up of three main modules.  The first module explores the concepts and typologies of money laundering and terrorist financing.  These concepts will be contextualised against the international efforts that been deployed to combat these illicit activities.  The Hong Kong AML and CTF framework, and the roles of the respective enforcement agencies, will also be discussed.  The second module examines the key components of a sound AML and CTF compliance programme in a financial institution.  The way how this programme should be embedded within the broader internal control, risk management, and governance framework will also be considered.  The third module focuses on some thematic issues of an AML and CTF compliance programme, including customer due diligence, escalation and exit strategies, suspicious activities, suspicious transaction reporting, and dealing with customers and regulators.

In this course, students will be learning through different activities.  Besides the lecture component, students will be provided with an opportunity to deliver presentations and participate in in-class discussion on different case studies and court cases.  Where appropriate, practitioners in the relevant field will be invited to share with students their experience and insights on how different AML and CTF issues come into play and handled in practice.

Assessment: 80% take home examination, 20% group presentation

Machine learning and artificial intelligence are the apex technologies of the information era. These methods are getting increasingly popular in the financial market. This course provides students the fundamental models and methods of machine learning and apply them to solve real-world financial problems. The topics include regression, classification, clustering methods, model selection, topic modelling and policy search. The first part of the course focuses on supervised learning techniques for regression and classification. The second part of the course covers unsupervised learning techniques for clustering and matrix factorisation. The third part of the course covers reinforcement learning algorithm. The last part provides the fundamental concepts of artificial intelligence and its implications. The course provides introductions to the latest datasets in financial markets and practices applying learning algorithms to these datasets in a variety of topics. The primary mode of learning is based on assignments and projects.

Assessment: 60% coursework and 40% examination

This course provides a foundation for advanced quantitative trading in financial markets.  The course has two parts.  First, the course reviews stylised facts and methods used for time-series predictability, cross-sectional asset pricing and strategy performance evaluation.  The second part of the course uses these tools to study recent advances in investment strategies sourcing from academic and practitioner literature.  For example, the course will discuss new theories on risk premia, intermediation-based asset pricing, and quantifiable soft information and alternative data.  The primary method of learning will be a combination of problem sets and projects.  Subject to availability, learning will be supplemented with exposure to industry speakers from the local financial industry.

Prerequisite: MFIN7002 Investment Analysis and Portfolio Management

Assessment: 100% coursework

This course covers statistical methods and models of importance to risk management, especially of Value-at-Risk (VaR).  Contents include: Value-at-risk (VaR) and Expected Shortfall (ES); univariate models (normal model, log-normal model and stochastic process model) for VaR and ES; models for portfolio VaR; time series models for VaR; extreme value approach to VaR; back-testing and stress testing.

Assessment: 50% coursework and 50% examination

Quantitative trading is a systematic investment approach that consists of identification of trading opportunities via statistical data analysis and implementation via computer algorithms.  This course introduces various methodologies that are commonly employed in quantitative trading.

The first half of the course focuses at strategies and methodologies derived from the data snapshotted at daily or minute frequency.  Some specific topics are: (1) techniques for trading trending and mean-reverting instruments, (2) statistical arbitrage and pairs trading, (3) detection of “time-series” mean reversion or stationarity, (4) cross-sectional momentum and contrarian strategies, (5) back-testing methodologies and corresponding performance measures, and (6) Kelly formula, money and risk management.  The second half of the course discusses statistical models of high frequency data and related trading strategies.  Topics that planned to be covered are: (7) introduction of market microstructure, (8) stylised features and models of high frequency transaction prices, (9) limit order book models, (10) optimal execution and smart order routing algorithms, and (11) regulation and compliance issues in algorithmic trading.

Pre-requisites: Pass in STAT6013 Financial data analysis or equivalent

Assessment: 50% coursework and 50% examination