Abstract: 

The economics and finance disciplines have traditionally relied on structured forms of data and linear models; however, there has recently been substantial progress in the integration of methods from machine learning and the use of unstructured data sources, such as text. This has coincided with a surge of applied machine learning research in economics, and an expansion of its use in industry. This talk will focus on some of the more successful applications of machine learning in economics and finance, and will be centered on the use of TensorFlow 2 in Python.

Our discussion will start with a brief overview of the value of machine learning in economic applications. We will then introduce TensorFlow 2 and discuss its advantages as a tool for solving prediction and modeling problems in economics and finance. The remainder of the presentation will be dedicated to two applications. The first will center on the use of natural language processing methods as a means of extracting text features from central bank communications, such as speeches and policy statements. The second will examine the use of generative adversarial networks (GANs) as a tool for simulating financial data for Monte Carlo experiments. Code will be provided for all worked examples included in the presentation.

Bio: 

Isaiah Hull is a senior economist in the research division of Sweden's Central Bank (Sveriges Riksbank). He holds a PhD in economics from Boston College and conducts research on computational economics, machine learning, and quantum computing. He is also the instructor for DataCamp's ""Introduction to TensorFlow in Python"" course and the author of ""Machine Learning for Economics in Finance in TensorFlow 2."