Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Artificial intelligence in financial markets : cutting edge applications for risk management, portfolio optimization and economics
Dunis C., Middleton P., Karathanasopolous A., Theofilatos K., Palgrave Macmillan, London, UK, 2016. 344 pp. Type: Book (978-1-137488-79-4)
Date Reviewed: Sep 20 2017

Focused on artificial intelligence and its application in finance, this book is the first volume in the series “New Developments in Quantitative Trading and Investment.”

Split into five sections, the first reviews artificially intelligent applications in finance, including the main techniques for the analysis of financial applications as parametric and nonparametric statistical methods and also soft computing (artificial neural networks, also known as advanced neural networks; fuzzy logic; support vector machines; and genetic algorithms). This section includes examples of applications of expert systems and hybrid intelligence in finance, and an appendix of frequently used data mining tools with sample code for some data mining techniques.

Part 2 includes four chapters. The first one talks about adaptive modeling and optimization techniques, presenting a novel methodology that proposes an “application of a sliding window machine learning approach for forecasting and trading the [Financial Times Stock Exchange (FTSE) 100 Index].” The authors say that “this is the first time that this adaptive [particle swarm optimization, PSO] algorithm has been combined with [a radial basis function neural network, RBFNN] to model and forecast an equity index.” The proposed method is presented with numeric examples.

Chapter 3 (“Modelling, Forecasting and Trading the Crack”) presents the benefits of using nonlinear modeling to train the network, using nonlinear modeling “over different sliding windows using both a PSO algorithm and a traditional backpropagation algorithm.” The aim of this chapter is to present the model in the crack spread, and to evaluate empirical results.

Chapter 4 introduces a tool for constructing trading strategies with gene expression programming. GEPTrader is “a new standalone free tool for constructing financial forecasting models using a variation of the gene expression programming (GEP) algorithm,” part of the category of evolutionary and genetic programming algorithms.

There is only one chapter in Part 3 (“Economics”): chapter 5 (“Business Intelligence for Decision Making in Economics”). This chapter presents the business-automated data economy model (BDM), “designed to improve the efficiency of closed funds by developing an algorithm that uses data from the US stock market.” The proposed model intends to help capture large amounts of data in order to provide viable solutions for decision making.

Part 4 (“Credit Risk and Analysis”) talks about credit risk assessment data mining literature analysis using automated methods. Chapter 7 (“Intelligent Credit Risk Decision Support: Architecture and Implementations”) presents the framework for credit risk evaluation, “complementing machine-learning-based credit risk [decision support systems, DSS] with additional components for financial metadata.” Chapter 8 (“Artificial Intelligence for Islamic Sukuk Rating Predictions”) talks about the Islamic finance and capital market, one of the fastest growing segments of the international financial market, and specifically about Sukuk, the Islamic securities model market. This chapter is about the comparison of multinomial logistics, decision trees, and a neural network model.

The last part of the book (Part 5, “Portfolio Management, Analysis, and Optimization”) has three chapters. Chapter 9 presents “a simulation-based survey that applies an interaction-based approach to examine portfolio selection as a multi-period choice problem under uncertainty,” and relates it to simulation-based games on social networks. Chapter 10 (“Handling Model Risk in Portfolio Selection Using Multi-Objective Genetic Algorithm”) presents a modified version of the multi-objective genetic algorithm (MOGA), which is applied to a set of stocks. The last chapter, 11, discusses the difference between the application of linear regression or fuzzy linear regression in the evaluation of the performance of mutual fund managers. The study presents two methodological approaches, ordinary least squares and fuzzy linear regression, and shows the mean differences between them.

This is an interesting book. The preface explains all of the content of the book, but there is an error. The authors say that the book has four parts, but there are actually five. They likely excluded Part 1, considering it as just an introduction, but the table of contents lists it as Part 1, “Introduction to Artificial Intelligence.” The book is a set of chapters that don’t have the same academic literature level. I could recommend this book to readers who are deeply interested in the application of AI to financial markets and who can tolerate chapters that are inconsistent with each other.

More reviews about this item: Amazon

Reviewer:  Agliberto Alves Cierco Review #: CR145553 (1711-0710)
Bookmark and Share
  Featured Reviewer  
 
Applications And Expert Systems (I.2.1 )
 
 
Connectionism And Neural Nets (I.2.6 ... )
 
 
Financial (J.1 ... )
 
 
Time Series Analysis (G.3 ... )
 
 
Learning (I.2.6 )
 
 
Probability And Statistics (G.3 )
 
Would you recommend this review?
yes
no
Other reviews under "Applications And Expert Systems": Date
Institutionalizing expert systems: a handbook for managers
Liebowitz J. (ed), Prentice-Hall, Inc., Upper Saddle River, NJ, 1991. Type: Book (9780134720777)
Nov 1 1991
Verifying and validating personal computer-based expert systems
Bahill A., Prentice-Hall, Inc., Upper Saddle River, NJ, 1991. Type: Book (9780139574573)
Jun 1 1992
Knowledge-based systems: a manager’s perspective
Tuthill G., Levy S., TAB Books, Blue Ridge Summit, PA, 1991. Type: Book (9780830634798)
Dec 1 1991
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy