Book Image

Machine Learning for Finance

By : Jannes Klaas
Book Image

Machine Learning for Finance

By: Jannes Klaas

Overview of this book

Machine Learning for Finance explores new advances in machine learning and shows how they can be applied across the financial sector, including insurance, transactions, and lending. This book explains the concepts and algorithms behind the main machine learning techniques and provides example Python code for implementing the models yourself. The book is based on Jannes Klaas’ experience of running machine learning training courses for financial professionals. Rather than providing ready-made financial algorithms, the book focuses on advanced machine learning concepts and ideas that can be applied in a wide variety of ways. The book systematically explains how machine learning works on structured data, text, images, and time series. You'll cover generative adversarial learning, reinforcement learning, debugging, and launching machine learning products. Later chapters will discuss how to fight bias in machine learning. The book ends with an exploration of Bayesian inference and probabilistic programming.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning for Finance
Jannes Klaas
May, 2019 | 456 pages
Small book image
Deep Learning Quick Reference
Michael Bernico
Mar, 2018 | 272 pages
Small book image
Hands-On Neural Networks with Keras
Niloy Purkait
Mar, 2019 | 462 pages
Small book image
Hands-On Machine Learning for Algorithmic Trading
Stefan Jansen
Dec, 2018 | 684 pages
Table of Contents (15 chapters)
Machine Learning for Finance
Machine Learning for Finance
Contributors
Contributors
Preface
Preface
Other Books You May Enjoy
Other Books You May Enjoy
Free Chapter
1
Neural Networks and Gradient-Based Optimization
Neural Networks and Gradient-Based Optimization
Our journey in this book
What is machine learning?
Supervised learning
Unsupervised learning
Reinforcement learning
Setting up your workspace
Using Kaggle kernels
Using the AWS deep learning AMI
Approximating functions
A forward pass
A logistic regressor
Optimizing model parameters
Measuring model loss
A deeper network
A brief introduction to Keras
Tensors and the computational graph
Exercises
Summary
2
Applying Machine Learning to Structured Data
Applying Machine Learning to Structured Data
The data
Heuristic, feature-based, and E2E models
The machine learning software stack
The heuristic approach
The feature engineering approach
Preparing the data for the Keras library
Creating predictive models with Keras
A brief primer on tree-based methods
E2E modeling
Exercises
Summary
3
Utilizing Computer Vision
Utilizing Computer Vision
Convolutional Neural Networks
Filters on color images
The building blocks of ConvNets in Keras
More bells and whistles for our neural network
Working with big image datasets
Working with pretrained models
The modularity tradeoff
Computer vision beyond classification
Exercises
Summary
4
Understanding Time Series
Understanding Time Series
Visualization and preparation in pandas
Fast Fourier transformations
Autocorrelation
Establishing a training and testing regime
A note on backtesting
Median forecasting
ARIMA
Kalman filters
Forecasting with neural networks
Conv1D
Dilated and causal convolution
Simple RNN
LSTM
Recurrent dropout
Bayesian deep learning
Exercises
Summary
5
Parsing Textual Data with Natural Language Processing
Parsing Textual Data with Natural Language Processing
An introductory guide to spaCy
Named entity recognition
Part-of-speech (POS) tagging
Rule-based matching
Regular expressions
A text classification task
Preparing the data
Bag-of-words
Topic modeling
Word embeddings
Document similarity with word embeddings
A quick tour of the Keras functional API
Attention
Seq2seq models
Exercises
Summary
6
Using Generative Models
Using Generative Models
Understanding autoencoders
Visualizing latent spaces with t-SNE
Variational autoencoders
VAEs for time series
GANs
Using less data – active learning
SGANs for fraud detection
Exercises
Summary
7
Reinforcement Learning for Financial Markets
Reinforcement Learning for Financial Markets
Catch – a quick guide to reinforcement learning
Markov processes and the bellman equation – A more formal introduction to RL
Advantage actor-critic models
Evolutionary strategies and genetic algorithms
Practical tips for RL engineering
Frontiers of RL
Exercises
Summary
8
Privacy, Debugging, and Launching Your Products
Privacy, Debugging, and Launching Your Products
Debugging data
Debugging your model
Deployment
Performance tips
Exercises
Summary
9
Fighting Bias
Fighting Bias
Sources of unfairness in machine learning
Legal perspectives
Observational fairness
Training to be fair
Causal learning
Interpreting models to ensure fairness
Unfairness as complex system failure
A checklist for developing fair models
Exercises
Summary
10
Bayesian Inference and Probabilistic Programming
Bayesian Inference and Probabilistic Programming
An intuitive guide to Bayesian inference
Summary
Farewell
Further reading
Index
Index

Using less data – active learning

Part of the motivation for generative models, be they GANs or VAEs, was always that they would allow us to generate data and therefore require less data. As data is inherently sparse, especially in finance, and we never have enough of it, generative models seem as though they are the free lunch that economists warn us about. Yet even the best GAN works with no data. In this section, we will have a look at the different methods used to bootstrap models with as little data as possible. This method is also called active learning or semi-supervised learning.

Unsupervised learning uses unlabeled data to cluster data in different ways. An example is autoencoders, where images can be transformed into learned and latent vectors, which can then be clustered without the need for labels that describe the image.

Supervised learning uses data with labels. An example is the image classifier we built in Chapter 3, Utilizing Computer Vision, or most of the other models...

Previous Section
End of Section 7
Next Section