Machine Learning for Economics and Finance in Tensorflow 2: Deep Learning Models for Research and Industry (Paperback)

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.

·      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

Chapter 4: Trees

Chapter Goal: Introduce tree-based models and the concept of ensembles.

·      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

·      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

·      Data preparation

·      Deep neural networks

·      Convolutional neural networks

·      Recurrent neural networks

·      Capsule networks

·      Pretrained models

Chapter 7: Text

Chapter Goal: Introduce text analysis, which has been applied extensively in economics. Cover the process of cleaning text and converting it into a numerical format, as well as a selection of unsupervised, supervised, and generative models. Discuss state-of-the-art models in the literature. 

·      The natural language toolkit

·      Data cleaning and preparation

·      Tokenization

·      The bag-of-words model

·      Sentiment analysis

·      Static and dynamic topic modeling

·      Text classification

·      Text generation

·      Pretrained models

Chapter 8: Time Series

Chapter Goal: Empirical work in macroeconomics and finance relies extensively on time series analysis. Methods from machine learning for sequential data analysis currently have low penetration in the economics literature. This chapter will speculate on how machine learning methods could be used in time series analysis.

·      Text and time series

·      Sequential models of machine learning

·      Recurrent neural networks

·      Long short-term memory

·      Model evaluation

·      Comparison with methods in economics and finance

Chapter 9: Dimensionality Reduction

Chapter Goal: Discuss dimensionality reduction as it is used in economics. Explain commonly used tools in machine learning for dimensionality reduction, including those which are also used in economics and finance.

·      Dimensionality reduction in economics

·      Partially linear regression

·      The autoencoder model

Chapter 10: Generative Models

Chapter Goal: Introduce the concept of generative machine learning, including a discussion of existing models. Review the few applications of generative machine learning in economics and finance and speculate on potential future uses.

·      Introduction to generative machine learning

·      Generative adversarial networks

·      Applications in economics and finance

Chapter 11: Theoretical Models

Chapter Goal: Discuss how theoretical models in economics and finance can be defined and solved using TensorFlow. Provide complete definitions and solutions for several workhorse models.

·      Defining mathematical models

·      Optimizers

·      Performance evaluation

·      Solving models in economics and finance