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

Chapter 4. Understanding Time Series

A time series is a form of data that has a temporal dimension and is easily the most iconic form of financial data out there. While a single stock quote is not a time series, take the quotes you get every day and line them up, and you get a much more interesting time series. Virtually all media materials related to finance sooner or later show a stock price gap; not a list of prices at a given moment, but a development of prices over time.

You'll often hear financial commenters discussing the movement of prices: "Apple Inc. is up 5%." But what does that mean? You'll hear absolute values a lot less, such as, "A share of Apple Inc. is $137.74." Again, what does that mean? This occurs because market participants are interested in how things will develop in the future and they try to extrapolate these forecasts from how things developed in the past:

Multiple time series graphs as seen on Bloomberg TV

Most forecasting that is done involves looking at past developments...