Identifying Patterns in Financial Markets | springerprofessional.de

Springer Professional

Top

2018 | Book

Read chapter Read first chapter

Identifying Patterns in Financial Markets

New Approach Combining Rules Between PIPs and SAX

Authors: Dr. João Leitão, Prof. Rui Ferreira Neves, Prof. Nuno C.G. Horta

Publisher: Springer International Publishing

Book Series : SpringerBriefs in Applied Sciences and Technology

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access

About this book

This book describes a new pattern discovery approach based on the combination among rules between Perceptually Important Points (PIPs) and the Symbolic Aggregate approximation (SAX) representation optimized by Genetic Algorithm (GA). The proposed approach was tested with real data from S&P500 index and all the results obtained outperform the Buy&Hold strategy. Three different case studies are presented by the authors.

Advertisement

Table of Contents

Frontmatter

Chapter 1. Introduction

Abstract

This chapter presents an overview of the work and its structure. In Sect. 1.1 the goals are described, in Sect. 1.2 the main improvements in the work’s subject area and in Sect. 1.3 the structure of this book is detailed.

João Leitão, Rui Ferreira Neves, Nuno C. G. Horta

Chapter 2. Related Work

Abstract

This chapter presents background information and reviews the existing literature that is relevant to the development of this project. The first part of this chapter presents a brief description of the two existing approaches to analyze the market, in Sect. 2.1 will be described in detail the fundamental and the technical analysis and its tools. A formal definition of an optimization methodology is given in Sect. 2.2. A review of the existence literature about pattern recognition/detection and its techniques to invest in the market is detailed in Sect. 2.3.

João Leitão, Rui Ferreira Neves, Nuno C. G. Horta

Chapter 3. SIR/GA Approach

Abstract

In this chapter, the new approach to pattern discovery will be presented in detail. The objective of this research is to develop a pattern discovery algorithm that combines ideas from how humans identify patterns and automatic classification of the patterns. The method uses points that normally a human would consider important and then creates rules to describe the relationship between them. Then using GA and SAX makes a search for the relevant patterns in order to detect opportunities to enter/exit the market. This new approach, Symbolic Important Rules (SIR), is based on two different ideas from the related work: PIPs with rules and SAX representation. Also, the system’s architecture and each of its modules that support this approach will be described later in this chapter.

João Leitão, Rui Ferreira Neves, Nuno C. G. Horta

Chapter 4. Experiments and Results

Abstract

In this chapter the experiments and the results of the SIR/GA approach, presented in the previous chapter, are described. Firstly in Sect. 4.1, the metrics used to evaluate the SIR/GA approach are presented and then in Sect. 4.2 three different case studies on the application of the proposed solution are presented.

João Leitão, Rui Ferreira Neves, Nuno C. G. Horta

Chapter 5. Conclusions and Future Work

Abstract

This chapter summarizes the main features of the new approach described and developed in this work, and also the goals achieved. Also, several topics are raised for a future improvement on this work.

João Leitão, Rui Ferreira Neves, Nuno C. G. Horta

Title: Identifying Patterns in Financial Markets
Authors: Dr. João Leitão
Prof. Rui Ferreira Neves
Prof. Nuno C.G. Horta
Copyright Year: 2018
Publisher: Springer International Publishing
Electronic ISBN: 978-3-319-70160-8
Print ISBN: 978-3-319-70159-2
DOI: https://doi.org/10.1007/978-3-319-70160-8

Premium Partner