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.
Table of Contents (15 chapters)
Machine Learning for Finance
Contributors
Preface
Other Books You May Enjoy
Index

Setting up your workspace


Before we can start, you will need to set up your workspace. The examples in this book are all meant to run in a Jupyter notebook. Jupyter notebooks are an interactive development environment mostly used for data-science applications and are considered the go-to environment to build data-driven applications in.

You can run Jupyter notebooks either on your local machine, on a server in the cloud, or on a website such as Kaggle.

Note

Note: All code examples for this book can be found here: https://github.com/PacktPublishing/Machine-Learning-for-Finance and for chapter 1 refer the following link: https://www.kaggle.com/jannesklaas/machine-learning-for-finance-chapter-1-code.

Deep learning is computer intensive, and the data used in the examples throughout this book are frequently over a gigabyte in size. It can be accelerated by the use of Graphics Processing Units (GPUs), which were invented for rendering video and games. If you have a GPU enabled computer, you can run the examples locally. If you do not have such a machine, it is recommended to use a service such as Kaggle kernels.

Learning deep learning used to be an expensive endeavor because GPUs are an expensive piece of hardware. While there are cheaper options available, a powerful GPU can cost up to $10,000 if you buy it and about $0.80 an hour to rent it in the cloud.

If you have many, long-running training jobs, it might be worth considering building a "deep learning" box, a desktop computer with a GPU. There are countless tutorials for this online and a decent box can be assembled for as little as a few hundred dollars all the way to $5,000.

The examples in this book can all be run on Kaggle for free, though. In fact, they have been developed using this site.