Chapter 1: TensorFlow 2.0
Chapter Goal: Introduce TensorFlow 2 and discuss preliminary material on conventions and practices specific to TensorFlow.
- Differences between TensorFlow iterations
- TensorFlow for economics and finance
- Introduction to tensors
- Review of linear algebra and calculus
- Loading data for use in TensorFlow
- Defining constants and variables
Chapter 2: Machine Learning and Economics
Chapter Goal: Provide a high-level overview of machine learning models and explain how they can be employed in economics and finance. Part of the chapter will review existing work in economics and speculate on future use-cases.
- Introduction to machine learning- Machine learning for economics and finance
- Unsupervised machine learning
- Supervised machine learning
- Regularization
- Prediction
- Evaluation
Chapter 3: Regression
Chapter Goal: Explain how regression models are used primarily for prediction purposes in machine learning, rather than hypothesis testing, as is the case in economics. Introduce evaluation metrics and optimization routines used to solve regression models.
- Linear regression
- Partially-linear regression
- Non-linear regression
- Logistic regression
- Loss functions
- Evaluation metrics
- Optimizers
Chapter 4: Trees
Chapter Goal: Introduce tree-based models and the concept of ensembles.
- Decision trees- Regression trees
- Random forests
- Model tuning
Chapter 5: Gradient Boosting
Chapter Goal: Introduce gradient boosting and discuss how it is applied, how models are tuned, and how to identify important features.
- Introduction to gradient boosting
- Boosting with regression models
- Boosting with trees- Model tuning
- Feature importance
Chapter 6: Images
Chapter Goal: Introduce the high level Keras and Estimators APIs. Explain how these libraries can be used to perform image classification using a variety of deep learning models. Also, discuss the use of pretrained models and fine-tuning. Speculate on image classification uses in economics and finance.
- Keras
- Estimators- Data preparation
- Deep neural networ
About the Author: Isaiah Hull received his PhD in Economics from Boston College in 2013 and has since worked in the Research Division at Sweden's Central Bank. He has published numerous articles in academic journals primarily concentrated in computational economics with applications in macroeconomics, finance, and housing. Most of his recent work makes use of techniques from machine learning. He also regularly presents at conferences on machine learning and big data in economics. And Isaiah is an accomplished teacher with experience teaching TensorFlow 2.0. Currently, he's working on a project to introduce quantum computing to economists.
