Machine Learning for Economics and Finance in TensorFlow 2

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 networks

·      Convolutional neural networks

·      Recurrent neural networks

·      Capsule networks

·      Pretrained models·      Model fine-tuning



 

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·      Word embeddings



·      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·      Forecasting



·      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·      Principal component analysis



·      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·      Variational autoencoders



·      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·      Automatic differentiation



·      Optimizers

·      Performance evaluation

·      Solving models in economics and finance