Course Introduction:

This course introduces the basic statistics and principles behind different contemporary models in deep learning with applications in business. Emphasis is put on various topics on multilayer artificial neural networks, such as Convolutional Neural Network (CNN), Generative Adversarial Networks (GAN) and Recurrent Neural Network (RNN), and also Reinforcement Learning (RL). About their usage, CNN brings new insights into image classification, and also helps to digitalize business information; GAN finds wide applications in speech recognition and text-mining; RNN is very useful for hand-writing recognition; reinforcement learning enables effective decision making in rapidly changing environments such as financial markets. Statistical packages including R, EXCEL and Python will be used to demonstrate these methods. Examples from financial and business contexts will be accentuated in this course. The students taking this course are expected to have acquired basic background knowledge on calculus, linear algebra, probability and statistics as prerequisites.

Tutorial Notes:

Tutorial 1: Introduction to Deep Learning and its Applications in Finance

Tutorial 2: Review of Calculus, Linear Algebra and Quadratic Programming

Tutorial 3: Matrix Theory, Quadratic Programming and Regression in Python

Tutorial 4: Model Assessment and Hyperparamerer tuning

Tutorial 5: Feature Engineering and Imbalance Dataset