#### 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.
Machine Learning for Finance
Contributors
Preface
Other Books You May Enjoy
Free Chapter
Applying Machine Learning to Structured Data
Utilizing Computer Vision
Understanding Time Series
Parsing Textual Data with Natural Language Processing
Using Generative Models
Reinforcement Learning for Financial Markets
Privacy, Debugging, and Launching Your Products
Fighting Bias
Bayesian Inference and Probabilistic Programming
Index

## Fast Fourier transformations

Another interesting statistic we often want to compute about time series is the Fourier transformation (FT). Without going into the math, a Fourier transformation will show us the amount of oscillation within a particular frequency in a function.

You can imagine this like the tuner on an old FM radio. As you turn the tuner, you search through different frequencies. Every once in a while, you find a frequency that gives you a clear signal of a particular radio station. A Fourier transformation basically scans through the entire frequency spectrum and records at what frequencies there is a strong signal. In terms of a time series, this is useful when trying to find periodic patterns in the data.

Imagine that we found out that a frequency of one per week gave us a strong pattern. This would mean that knowledge about what the traffic was ton the same day one week ago would help our model.

When both the function and the Fourier transform are discrete, which is the case...