Grammar-Based Feature Generation for Time-Series Prediction

  • Anthony Mihirana De Silva
  • Philip H. W. Leong

Part of the SpringerBriefs in Applied Sciences and Technology book series (BRIEFSAPPLSCIENCES)

Also part of the SpringerBriefs in Computational Intelligence book sub series (BRIEFSINTELL)

Table of contents

  1. Front Matter
    Pages i-xi
  2. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 1-11
  3. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 13-24
  4. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 25-33
  5. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 35-50
  6. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 51-62
  7. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 63-83
  8. Anthony Mihirana De Silva, Philip H. W. Leong
    Pages 85-87
  9. Back Matter
    Pages 89-99

About this book

Introduction

This book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method can be applied to a wide range of machine learning architectures and applications to represent complex feature dependencies explicitly when machine learning cannot achieve this by itself. Industrial applications can use the proposed technique to improve their predictions.

Keywords

Context-Free Grammar Feature Generation Feature Selection Grammatical Evolution Time-Series Prediction

Authors and affiliations

  • Anthony Mihirana De Silva
    • 1
  • Philip H. W. Leong
    • 2
  1. 1.Electrical and Information EngineeringUniversity of SydneySydneyAustralia
  2. 2.Electrical and Information EngineeringUniversity of SydneyEast KillaraAustralia

Bibliographic information

  • DOI https://doi.org/10.1007/978-981-287-411-5
  • Copyright Information The Author(s) 2015
  • Publisher Name Springer, Singapore
  • eBook Packages Engineering
  • Print ISBN 978-981-287-410-8
  • Online ISBN 978-981-287-411-5
  • Series Print ISSN 2191-530X
  • Series Online ISSN 2191-5318
  • About this book