SpringerBriefs in Computational Intelligence

Grammar-Based Feature Generation for Time-Series Prediction

Authors: De Silva, Anthony Mihirana, Leong, Philip H. W.

  • First book presenting the framework for context-free grammar-based feature generation
  • Equips readers to predict time-series prediction using machine learning techniques
  • Includes case studies that illustrate the performance of different machine learning and model based approaches on financial, electrical and foreign exchange client trade volume time-series data
see more benefits

Buy this book

eBook $59.99
price for USA (gross)
  • ISBN 978-981-287-411-5
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Softcover $74.99
price for USA
  • ISBN 978-981-287-410-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

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.

Table of contents (7 chapters)

  • Introduction

    De Silva, Anthony Mihirana (et al.)

    Pages 1-11

  • Feature Selection

    De Silva, Anthony Mihirana (et al.)

    Pages 13-24

  • Grammatical Evolution

    De Silva, Anthony Mihirana (et al.)

    Pages 25-33

  • Grammar Based Feature Generation

    De Silva, Anthony Mihirana (et al.)

    Pages 35-50

  • Application of Grammar Framework to Time-Series Prediction

    De Silva, Anthony Mihirana (et al.)

    Pages 51-62

Buy this book

eBook $59.99
price for USA (gross)
  • ISBN 978-981-287-411-5
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Softcover $74.99
price for USA
  • ISBN 978-981-287-410-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Grammar-Based Feature Generation for Time-Series Prediction
Authors
Series Title
SpringerBriefs in Computational Intelligence
Copyright
2015
Publisher
Springer Singapore
Copyright Holder
The Author(s)
eBook ISBN
978-981-287-411-5
DOI
10.1007/978-981-287-411-5
Softcover ISBN
978-981-287-410-8
Series ISSN
2520-8551
Edition Number
1
Number of Pages
XI, 99
Number of Illustrations and Tables
28 b/w illustrations
Topics