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
Other Books You May Enjoy

Debugging your model

Complex deep learning models are prone to error. With millions of parameters, there are a number things that can go wrong. Luckily, the field has developed a number of useful tools to improve model performance. In this section, we will introduce the most useful tools that you can use to debug and improve your model.

Hyperparameter search with Hyperas

Manually tuning the hyperparameters of a neural network can be a tedious task. Despite you possibly having some intuition about what works and what does not, there are no hard rules to apply when it comes to tuning hyperparameters. This is why practitioners with lots of computing power on hand use automatic hyperparameter search. After all, hyperparameters form a search space just like the model's parameters do. The difference is that we cannot apply backpropagation to them and cannot take derivatives of them. We can still apply all non-gradient based optimization algorithms to them.

There are a number of different hyperparameter...