Grammar-Based Feature Generation for Time-Series Prediction

Grammar-Based Feature Generation for Time-Series Prediction

4.11 - 1251 ratings - Source

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.The results are discussed under three sections for stock market index time-series, electricity load demand time-series and foreign exchange client trade volume time-series. ... The system performance was assessed on the daily closing prices of leading financial stock indices in Table6.1. The data were downloaded from a€œ Yahoo! Financea€ using the quantmod package in R [1] and comprise of daily recordings between 16 October 1998 and 19 June 2006 (1, 900 trading days). The dataanbsp;...

Title:Grammar-Based Feature Generation for Time-Series Prediction
Author: Anthony Mihirana De Silva, Philip H. W. Leong
Publisher:Springer - 2015-02-14

You must register with us as either a Registered User before you can Download this Book. You'll be greeted by a simple sign-up page.

Once you have finished the sign-up process, you will be redirected to your download Book page.

How it works:
  • 1. Register a free 1 month Trial Account.
  • 2. Download as many books as you like (Personal use)
  • 3. Cancel the membership at any time if not satisfied.

Click button below to register and download Ebook
Privacy Policy | Contact | DMCA