Teaching

Courses:

  • Coding and Data Science for Accounting and Finance [FI505E]

This course will bring you from the very basics of coding in Python through to advanced data science topics like machine learning in order to equip you with the skills needed to play an active role in the new opportunities that these developments introduce to working in finance. This course is delivered in a non-conventional manner. There are 3 three-hour introductory sessions at the start of Semester 1, after which you will be expected to self-learn an online module to prepare you in the basics of Python coding. There will then be two consecutive six-hour sessions in November where you will apply your learning to the accounting and finance context in a Bootcamp style environment. Topics covered: • Introduction to data science in Finance • Fundamentals of Machine Learning in Finance • Coding in Python • Working with time series in Python • Machine learning with scikit-learn • Deep learning • Text mining

  • Neural Networks and Deep Learning for Finance [FI530E]

In this course, we teach the students a range of techniques to create scientific models from empirical data. The course consists of several lectures on data mining techniques with practical exercises in the class. Several lab exercises are designed to introduce the foundations and the application of deep learning in Finance. By finishing this course, students will learn how to work with Deep Learning models on big datasets. The course consists of 3 two-day blocks and final project presentation day. In the first block, students will learn the foundation of deep learning, and the second block focuses on applications of deep learning in Finance and managing machine learning projects. There is self-online learning between blocks. Each session includes lectures with following corresponding computer lab exercises. This course includes the following main topics: • Overview of Machine Learning methods • Fundamentals of Machine Learning in Finance • Python Programing • Neural Network: Feed-forward network • Recurrent network 6. Basic Idea of Deep Learning • Modern Practical Deep Networks • Application of Deep Learning in Finance • Deep Learning for Time Series data • Deep Learning for Textual Data

  • Data Science for Business

This course starts with the very basics of Python coding and works up modern advanced techniques such as machine learning and deep learning. The field of data science for business is the context for the class, and so applied business examples are the focus. The module has practicality at its heart, with students following the lessons using shared Python codebooks and implementing the techniques along with the professor.

  • Financial Data Infrastructure [FI532E]

It is essential to realize that today's students need formal training in areas beyond their central discipline; they need to know data management, computational sciences, and techniques. This means that students will have to understand financial data science much on a sufficient level. The future of social science involves the expansion of automation in all its aspects: data collection, storage of information, hypothesis formation, and experimentation. This course introduces tools for data analytics, machine learning for data analytics, and for exploring and visualizing data. It overviews the background of data analytics, covering the different types of analysis and the basics of using Hadoop as a tool. It focuses on various Hadoop ecosystem tools, like Apache Flume, Apache Spark, Apache Storm, Apache Hive, R, and Python, which can be used for different types of analysis. Students will also learn the machine learning techniques that are useful for data analytics and how to visualize data with various graphs and charts from a practice-oriented viewpoint. This course provides a reference guide -everything you need — including code samples — so you can get your hands dirty working with a real dataset and gain experience from financial projects. So after completing it, students will be able to work with different types of financial data structures.The course includes the following topics:
  • Big data and file formats (structured, unstructured, etc.), time series, text mining
  • Hadoop (an open-source platform for processing large datasets)
  • SQL and databases
  • Spark SQL in Python
  • Spark Machine Learning in Finance
  • Text mining
  • Financial Network

Prior Years' Courses:

Machine Learning in Finance, Management and Accounting (PhD Program)

In this course, we teach the students a range of techniques to create scientific models from empirical data. The course consists of several lectures on data mining techniques with practical exercises in the class. Several lab exercises are designed to introduce the application of data mining in social sciences. Students will learn how to work with big datasets and apply some advanced techniques in their own research field. After completing the course, students shall be able to independently draft an academic paper on key issues of social sciences by using machine learning techniques.
Course content:• Introduction to data mining: Supervised learning (prediction, classification), Unsupervised learning (associationanalysis, clustering), Regression, hypothesis test, descriptive statistics (Overview and background)• Introduction to R• Ridge regression, Principal components regression (PCA) Partial Least Squares regression (PLS)• Splines function, Kernel smoothers, Generalized Additive Models (GAM)• Classification methods Support Vector Machine (SVM), CART and MARS• Tree-based methods and Random Forests• Clustering methods• Neural networks and Deep learning• Text mining• Application of machine learning ( Finance, Business, Accounting, )

Mathematics : Bachelor Program

Teacher Assistance 2012-2016:

Mathematics for PhD ProgramStatistics and Econometric (Master of Finance )The principle of Statistics (Master in Management)Principles of Finance (Master of International Business)Market Estimation and Forecasting (Master of Finance)Econometric (Bachelor's Program (BSc))Advanced Derivative ( Master of Quantitative Finance)