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.