Book Image

Hands-On Artificial Intelligence for Banking

By : Jeffrey Ng, Subhash Shah
Book Image

Hands-On Artificial Intelligence for Banking

By: Jeffrey Ng, Subhash Shah

Overview of this book

Remodeling your outlook on banking begins with keeping up to date with the latest and most effective approaches, such as artificial intelligence (AI). Hands-On Artificial Intelligence for Banking is a practical guide that will help you advance in your career in the banking domain. The book will demonstrate AI implementation to make your banking services smoother, more cost-efficient, and accessible to clients, focusing on both the client- and server-side uses of AI. You’ll begin by understanding the importance of artificial intelligence, while also gaining insights into the recent AI revolution in the banking industry. Next, you’ll get hands-on machine learning experience, exploring how to use time series analysis and reinforcement learning to automate client procurements and banking and finance decisions. After this, you’ll progress to learning about mechanizing capital market decisions, using automated portfolio management systems and predicting the future of investment banking. In addition to this, you’ll explore concepts such as building personal wealth advisors and mass customization of client lifetime wealth. Finally, you’ll get to grips with some real-world AI considerations in the field of banking. By the end of this book, you’ll be equipped with the skills you need to navigate the finance domain by leveraging the power of AI.
Table of Contents (14 chapters)
Section 1: Quick Review of AI in the Finance Industry
Section 2: Machine Learning Algorithms and Hands-on Examples

Portfolio construction using the Treynor-Black model

Let's say we are given 10 days of pricing data, and the work of technical analysis is to draw the lines on the right to make sense of the trend in order to generate the next day's pricing for the 11th day. It is quite obvious to find that it is indeed what a convolutional neural network could tackle.

Knowing that, practically, the time unit we are looking at could be per 100 ms or 10 ms instead of 1 day, but the principle will be the same:

Let's continue with the Duke Energy example. In this hypothetical case, we assume that we are the treasurer running the pension fund plan of Duke Energy with a total asset size of 15 billion USD with a defined contribution plan. Presumably, we know what our IPS is in digital format:

  • Target return = 5% of real return (that means deducting the inflation of goods)
  • Risk = return volatility equals 10%
  • ...