This applied data science module aims to covers the theoretical, computational and statistical underpinnings of the machine & deep learning techniques. Applications of different algorithms with an emphasise on economics and finance will be discussed. Statistical techniques and learning methods that can lend itself to patterns and relationships in data will be introduced in this module. The size, complexity, and diversity of data increase every day. This means we need new solutions for analyzing data. Big data and statistical learning methods provide a vehicle for modeling and analyzing complex phenomena and for incorporating rich sources of confounding information into economic models. Finding patterns and relationships in large volumes of data are very useful in market research, business forecasting, decision support, and customer recommendation engines among other applications. Integration of these algorithms to business analytics frameworks will be demonstrated using real-world examples. Course demonstrations will be in Python, and for showcases and exercises, we make use of python scientific libraries. We also expose students to Google Colab so they can develop their coding skills by completing practical exercises on Colab. The data sets we will use for this course are from World Bank Group, Kaggle, Federal Reserve Economic Data, Google Finance, and several other resources. For the sake of learning, we will apply the algorithms and topics step by step to the problem, both in standard python libraries and from scratch.
The goal of this module is to give an applied, hands-on introduction to machine and deep learning methods. At the end of the course, students will be able to read and understand theoretical papers on the subject, to implement the techniques themselves in Python, and to apply the techniques to data used in economics and business. The style will be first to describe the theory and math behind algorithms and then demonstrate how to use Python to create and run the models. This course will introduce the student to classic machine learning algorithms and deep neural network structures, Autoencoders, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations.